Hybrid Arima - LSTM code - Covid

The hybrid ARIMA-LSTM model is open to a variety of experimentation. For ideal performance, a balance must be reached between the levels of volatility that work best for the ARIMA and LSTM models. Using shorter MA periods that result in a non-mesokurtic distribution may achieve a better volatility balance between models.

Import Libraries

In [1]:
import pandas as pd
pd.set_option('display.max_rows', 500)
import timeit
In [2]:
!pip install -q -U keras-tuner

     |████████████████████████████████| 98 kB 2.0 MB/s
In [3]:
import keras_tuner as kt
In [4]:
!pip install pmdarima

Collecting pmdarima
  Downloading pmdarima-1.8.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl (1.4 MB)
     |████████████████████████████████| 1.4 MB 5.1 MB/s 
Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.1.0)
Collecting statsmodels!=0.12.0,>=0.11
  Downloading statsmodels-0.13.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.8 MB)
     |████████████████████████████████| 9.8 MB 25.3 MB/s 
Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.4.1)
Requirement already satisfied: pandas>=0.19 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.1.5)
Requirement already satisfied: setuptools!=50.0.0,>=38.6.0 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (57.4.0)
Requirement already satisfied: urllib3 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.24.3)
Requirement already satisfied: scikit-learn>=0.22 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.0.1)
Requirement already satisfied: Cython!=0.29.18,>=0.29 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (0.29.24)
Requirement already satisfied: numpy>=1.19.3 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.19.5)
Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.19->pmdarima) (2018.9)
Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.19->pmdarima) (2.8.2)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.7/dist-packages (from python-dateutil>=2.7.3->pandas>=0.19->pmdarima) (1.15.0)
Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn>=0.22->pmdarima) (3.0.0)
Requirement already satisfied: patsy>=0.5.2 in /usr/local/lib/python3.7/dist-packages (from statsmodels!=0.12.0,>=0.11->pmdarima) (0.5.2)
Installing collected packages: statsmodels, pmdarima
  Attempting uninstall: statsmodels
    Found existing installation: statsmodels 0.10.2
    Uninstalling statsmodels-0.10.2:
      Successfully uninstalled statsmodels-0.10.2
Successfully installed pmdarima-1.8.4 statsmodels-0.13.1
In [5]:
import pmdarima
In [6]:
url = 'https://launchpad.net/~mario-mariomedina/+archive/ubuntu/talib/+files'
!wget $url/libta-lib0_0.4.0-oneiric1_amd64.deb -qO libta.deb
!wget $url/ta-lib0-dev_0.4.0-oneiric1_amd64.deb -qO ta.deb
!dpkg -i libta.deb ta.deb
!pip install ta-lib
import talib

Selecting previously unselected package libta-lib0.
(Reading database ... 155222 files and directories currently installed.)
Preparing to unpack libta.deb ...
Unpacking libta-lib0 (0.4.0-oneiric1) ...
Selecting previously unselected package ta-lib0-dev.
Preparing to unpack ta.deb ...
Unpacking ta-lib0-dev (0.4.0-oneiric1) ...
Setting up libta-lib0 (0.4.0-oneiric1) ...
Setting up ta-lib0-dev (0.4.0-oneiric1) ...
Processing triggers for man-db (2.8.3-2ubuntu0.1) ...
Processing triggers for libc-bin (2.27-3ubuntu1.3) ...
/sbin/ldconfig.real: /usr/local/lib/python3.7/dist-packages/ideep4py/lib/libmkldnn.so.0 is not a symbolic link

Collecting ta-lib
  Downloading TA-Lib-0.4.22.tar.gz (268 kB)
     |████████████████████████████████| 268 kB 5.0 MB/s 
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
    Preparing wheel metadata ... done
Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from ta-lib) (1.19.5)
Building wheels for collected packages: ta-lib
  Building wheel for ta-lib (PEP 517) ... done
  Created wheel for ta-lib: filename=TA_Lib-0.4.22-cp37-cp37m-linux_x86_64.whl size=1465642 sha256=97d5d24870f78eb9e3d82aaa24198e2edf91c684ef71eff65c674508b72e9de4
  Stored in directory: /root/.cache/pip/wheels/7b/63/a9/144081748d9c4f0a09b4670c7b3c414bcb33ff97f0724c753a
Successfully built ta-lib
Installing collected packages: ta-lib
Successfully installed ta-lib-0.4.22
In [7]:
import tensorflow
import statsmodels.tsa.api
import keras
import sklearn
In [8]:
from tensorflow.keras.optimizers import Adam
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, LSTM, Dropout, Bidirectional,BatchNormalization, Embedding, TimeDistributed, LeakyReLU, GRU
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau
In [9]:
from keras.models import Sequential, load_model
from keras.layers import Dense, LSTM, Activation, Dropout
from keras import backend as K
from keras.utils.generic_utils import get_custom_objects
from keras.callbacks import ModelCheckpoint,EarlyStopping
from keras.regularizers import l1_l2
In [10]:
import math
In [11]:
from statsmodels.tsa.api import VAR
from statsmodels.tsa.statespace.varmax import VARMAX,VARMAXResults
In [12]:
from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error, mean_absolute_error
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
In [13]:
from matplotlib import pyplot
In [14]:
import json
import datetime
import pandas as pd
import numpy as np
import os
from scipy.stats import kurtosis
import pmdarima as pm
from pmdarima import auto_arima
from talib import abstract
import json
import matplotlib.pyplot as plt
# plt.rcParams.update({'font.size': 16})
from matplotlib.pyplot import figure
from numpy import array
from numpy import hstack
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Dense
from keras.layers import RepeatVector
from keras.layers import TimeDistributed
In [15]:
from keras.utils.generic_utils import get_custom_objects
from tensorflow.keras.utils import plot_model
In [16]:
import warnings
from statsmodels.tools.sm_exceptions import ConvergenceWarning
warnings.simplefilter('ignore', ConvergenceWarning)

Reference 1: https://towardsdatascience.com/time-series-forecasting-predicting-stock-prices-using-an-arima-model-2e3b3080bd70

Load Data

In [17]:
from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive
In [18]:
cd drive/MyDrive/Stock price prediction/Generated datasets

/content/drive/.shortcut-targets-by-id/1IaGjVBlTspxI2CHSrxfYnaiYvsaG0pHs/Stock price prediction/Generated datasets
In [19]:
df = pd.read_csv("FULL_Data_google_COVID_bull_bear.csv",parse_dates=[0])
df.tail(10)
Out[19]:
Unnamed: 0 Unnamed: 0.1 Unnamed: 0.1.1 Unnamed: 0.1.1.1 Open High Low Close Adj Close Volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp Date search COVID positiveIncrease COVID deathIncrease bull score bear score fourier bull 10 fourier bull 30 fourier bear 10 fourier bear 30
1592 1592 1781 1781 1781 150.199997 151.429993 150.059998 150.809998 150.809998 56787900.0 150.565717 148.423811 -1.137777 2.817933 154.059677 142.787944 150.767809 5.009368 93.428749 -0.061228 100.779503 -0.039111 103.599003 -0.022436 2021-11-09 19 112313 1258 0.119141 0.111328 NaN NaN NaN NaN
1593 1593 1782 1782 1782 150.020004 150.130005 147.850006 147.919998 147.919998 65187100.0 150.417145 148.729049 -1.236913 2.144358 153.017766 144.440332 148.869268 4.989888 92.922909 -0.061683 99.694365 -0.039762 101.872301 -0.022657 2021-11-10 19 80301 1470 0.154297 0.109375 NaN NaN NaN NaN
1594 1594 1783 1783 1783 148.960007 149.429993 147.679993 147.869995 147.869995 41000000.0 150.110001 149.060477 -1.165047 1.767475 152.595428 145.525526 148.203086 4.989548 92.416471 -0.062129 98.604584 -0.040391 100.137594 -0.022839 2021-11-11 19 94975 1662 0.102845 0.126915 NaN NaN NaN NaN
1595 1595 1784 1784 1784 148.429993 150.399994 147.479996 149.990005 149.990005 63632600.0 149.895715 149.357144 -0.869308 1.420732 152.198608 146.515681 149.394365 5.003879 91.909483 -0.062566 97.510555 -0.040998 98.396260 -0.022980 2021-11-12 19 55499 797 0.157277 0.080595 NaN NaN NaN NaN
1596 1596 1785 1785 1785 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 2021-11-13 19 146529 2505 0.139459 0.083243 NaN NaN NaN NaN
1597 1597 1786 1786 1786 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN 2021-11-14 19 40964 479 0.151261 0.100840 NaN NaN NaN NaN
1598 1598 1787 1787 1787 150.369995 151.880005 149.429993 150.000000 150.000000 59222800.0 149.758571 149.602859 -0.907641 1.229694 152.062246 147.143471 149.798122 5.003946 91.401994 -0.062993 96.412672 -0.041581 96.649685 -0.023077 2021-11-15 22 30290 148 0.136737 0.109389 NaN NaN NaN NaN
1599 1599 1788 1788 1788 149.940002 151.490005 149.339996 151.000000 151.000000 59256200.0 149.718571 149.814763 -0.791320 1.236243 152.287250 147.342277 150.599374 5.010635 90.894052 -0.063410 95.311334 -0.042140 94.899260 -0.023130 2021-11-16 22 138962 1294 0.135531 0.115385 NaN NaN NaN NaN
1600 1600 1789 1789 1789 151.000000 155.000000 150.990005 153.490005 153.490005 88807000.0 150.154286 150.040002 -0.657719 1.467121 152.974245 147.105759 152.526461 5.027099 90.385704 -0.063817 94.206941 -0.042673 93.146378 -0.023135 2021-11-17 22 87626 1290 0.100870 0.126957 NaN NaN NaN NaN
1601 1601 1790 1790 1790 153.710007 158.669998 153.050003 157.869995 157.869995 137659100.0 151.162857 150.450002 -0.609656 2.267825 154.985653 145.914351 156.088817 5.055417 89.877000 -0.064214 93.099895 -0.043179 91.392433 -0.023090 2021-11-18 22 111404 1637 0.145098 0.121569 NaN NaN NaN NaN
In [82]:
cd ..

/content/drive/.shortcut-targets-by-id/1IaGjVBlTspxI2CHSrxfYnaiYvsaG0pHs/Stock price prediction
In [83]:
cd Archana - LSTM Hybrid/Outputs/CovidShare

/content/drive/.shortcut-targets-by-id/1IaGjVBlTspxI2CHSrxfYnaiYvsaG0pHs/Stock price prediction/Archana - LSTM Hybrid/Outputs/Covid
In [26]:
pd.to_datetime(df[np.isnan(df.Close)==True]['Date']).dt.day_name().head(5)
Out[26]:
0    Saturday
1      Sunday
3     Tuesday
7    Saturday
8      Sunday
Name: Date, dtype: object
In [27]:
len(pd.to_datetime(df[np.isnan(df.Close)==True]['Date']).dt.day_name())
Out[27]:
497
In [28]:
len(df)
Out[28]:
1602
In [29]:
len(df) - len(pd.to_datetime(df[np.isnan(df.Close)==True]['Date']).dt.day_name())
Out[29]:
1105
In [30]:
df.dropna(inplace=True)
len(df)
Out[30]:
1080
In [31]:
pd.to_datetime(df[np.isnan(df.Close)==True]['Date']).dt.day_name().head(3)
Out[31]:
Series([], Name: Date, dtype: object)
In [32]:
df.head(5)
Out[32]:
Unnamed: 0 Unnamed: 0.1 Unnamed: 0.1.1 Unnamed: 0.1.1.1 Open High Low Close Adj Close Volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp Date search COVID positiveIncrease COVID deathIncrease bull score bear score fourier bull 10 fourier bull 30 fourier bear 10 fourier bear 30
2 2 191 191 191 36.220001 36.325001 35.775002 35.875000 34.054882 57111200.0 36.173571 36.751904 0.303356 0.960520 38.672945 34.830864 35.924548 3.551770 38.458011 0.046984 29.704545 0.102857 43.304973 -0.053955 2017-07-03 15 0 0 0.666667 0.000000 0.142778 0.146810 0.100537 0.099251
4 4 193 193 193 35.922501 36.197498 35.680000 36.022499 34.194897 86278400.0 36.095357 36.634762 0.328795 0.852735 38.340231 34.929292 35.989849 3.555991 38.240991 0.049445 29.954520 0.099254 43.438321 -0.053936 2017-07-05 15 0 0 0.400000 0.000000 0.144487 0.145833 0.100630 0.096361
5 5 194 194 194 35.755001 35.875000 35.602501 35.682499 33.872143 96515200.0 35.984999 36.495238 0.346702 0.677629 37.850495 35.139980 35.784949 3.546235 38.027974 0.051918 30.209839 0.095602 43.557403 -0.053820 2017-07-06 15 0 0 0.142857 0.142857 0.145346 0.145164 0.100672 0.094761
6 6 195 195 195 35.724998 36.187500 35.724998 36.044998 34.216255 76806800.0 36.001071 36.362023 0.387422 0.387634 37.137291 35.586756 35.958315 3.556633 37.818962 0.054401 30.470232 0.091907 43.662260 -0.053608 2017-07-07 15 0 0 0.333333 0.000000 0.146208 0.144377 0.100711 0.093072
9 9 198 198 198 36.027500 36.487499 35.842499 36.264999 34.425095 84362400.0 35.973571 36.243809 0.388315 0.308042 36.859893 35.627725 36.162771 3.562891 37.613953 0.056893 30.735430 0.088177 43.752965 -0.053302 2017-07-10 14 0 0 0.000000 0.000000 0.148802 0.141354 0.100808 0.087587
In [33]:
stock_col= list(df.columns)
stock_col = stock_col[4:len(stock_col)]
In [34]:
dataset_final = df[stock_col]
In [35]:
dataset_final.head(5)
Out[35]:
Open High Low Close Adj Close Volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp Date search COVID positiveIncrease COVID deathIncrease bull score bear score fourier bull 10 fourier bull 30 fourier bear 10 fourier bear 30
2 36.220001 36.325001 35.775002 35.875000 34.054882 57111200.0 36.173571 36.751904 0.303356 0.960520 38.672945 34.830864 35.924548 3.551770 38.458011 0.046984 29.704545 0.102857 43.304973 -0.053955 2017-07-03 15 0 0 0.666667 0.000000 0.142778 0.146810 0.100537 0.099251
4 35.922501 36.197498 35.680000 36.022499 34.194897 86278400.0 36.095357 36.634762 0.328795 0.852735 38.340231 34.929292 35.989849 3.555991 38.240991 0.049445 29.954520 0.099254 43.438321 -0.053936 2017-07-05 15 0 0 0.400000 0.000000 0.144487 0.145833 0.100630 0.096361
5 35.755001 35.875000 35.602501 35.682499 33.872143 96515200.0 35.984999 36.495238 0.346702 0.677629 37.850495 35.139980 35.784949 3.546235 38.027974 0.051918 30.209839 0.095602 43.557403 -0.053820 2017-07-06 15 0 0 0.142857 0.142857 0.145346 0.145164 0.100672 0.094761
6 35.724998 36.187500 35.724998 36.044998 34.216255 76806800.0 36.001071 36.362023 0.387422 0.387634 37.137291 35.586756 35.958315 3.556633 37.818962 0.054401 30.470232 0.091907 43.662260 -0.053608 2017-07-07 15 0 0 0.333333 0.000000 0.146208 0.144377 0.100711 0.093072
9 36.027500 36.487499 35.842499 36.264999 34.425095 84362400.0 35.973571 36.243809 0.388315 0.308042 36.859893 35.627725 36.162771 3.562891 37.613953 0.056893 30.735430 0.088177 43.752965 -0.053302 2017-07-10 14 0 0 0.000000 0.000000 0.148802 0.141354 0.100808 0.087587

Data Load for Experiments with Technical Indicators & Covid

In [36]:
stock_col= list(df.columns)
stock_col1 = stock_col[4:len(stock_col)-9]
stock_col2 = stock_col[len(stock_col)-8:len(stock_col)-6]
stock_col1.append(stock_col2[0])
stock_col1.append(stock_col2[1])
dataset_final = df[stock_col1]
dataset_final.head(5)
Out[36]:
Open High Low Close Adj Close Volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp Date COVID positiveIncrease COVID deathIncrease
2 36.220001 36.325001 35.775002 35.875000 34.054882 57111200.0 36.173571 36.751904 0.303356 0.960520 38.672945 34.830864 35.924548 3.551770 38.458011 0.046984 29.704545 0.102857 43.304973 -0.053955 2017-07-03 0 0
4 35.922501 36.197498 35.680000 36.022499 34.194897 86278400.0 36.095357 36.634762 0.328795 0.852735 38.340231 34.929292 35.989849 3.555991 38.240991 0.049445 29.954520 0.099254 43.438321 -0.053936 2017-07-05 0 0
5 35.755001 35.875000 35.602501 35.682499 33.872143 96515200.0 35.984999 36.495238 0.346702 0.677629 37.850495 35.139980 35.784949 3.546235 38.027974 0.051918 30.209839 0.095602 43.557403 -0.053820 2017-07-06 0 0
6 35.724998 36.187500 35.724998 36.044998 34.216255 76806800.0 36.001071 36.362023 0.387422 0.387634 37.137291 35.586756 35.958315 3.556633 37.818962 0.054401 30.470232 0.091907 43.662260 -0.053608 2017-07-07 0 0
9 36.027500 36.487499 35.842499 36.264999 34.425095 84362400.0 35.973571 36.243809 0.388315 0.308042 36.859893 35.627725 36.162771 3.562891 37.613953 0.056893 30.735430 0.088177 43.752965 -0.053302 2017-07-10 0 0
In [37]:
# Set the date to datetime data
datetime_series = pd.to_datetime(dataset_final['Date'])
datetime_index = pd.DatetimeIndex(datetime_series.values)
dataset_final = dataset_final.set_index(datetime_index)
dataset_final = dataset_final.sort_values(by='Date')
dataset_final = dataset_final.drop(columns='Date')
dataset_final.head(5)
Out[37]:
Open High Low Close Adj Close Volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp COVID positiveIncrease COVID deathIncrease
2017-07-03 36.220001 36.325001 35.775002 35.875000 34.054882 57111200.0 36.173571 36.751904 0.303356 0.960520 38.672945 34.830864 35.924548 3.551770 38.458011 0.046984 29.704545 0.102857 43.304973 -0.053955 0 0
2017-07-05 35.922501 36.197498 35.680000 36.022499 34.194897 86278400.0 36.095357 36.634762 0.328795 0.852735 38.340231 34.929292 35.989849 3.555991 38.240991 0.049445 29.954520 0.099254 43.438321 -0.053936 0 0
2017-07-06 35.755001 35.875000 35.602501 35.682499 33.872143 96515200.0 35.984999 36.495238 0.346702 0.677629 37.850495 35.139980 35.784949 3.546235 38.027974 0.051918 30.209839 0.095602 43.557403 -0.053820 0 0
2017-07-07 35.724998 36.187500 35.724998 36.044998 34.216255 76806800.0 36.001071 36.362023 0.387422 0.387634 37.137291 35.586756 35.958315 3.556633 37.818962 0.054401 30.470232 0.091907 43.662260 -0.053608 0 0
2017-07-10 36.027500 36.487499 35.842499 36.264999 34.425095 84362400.0 35.973571 36.243809 0.388315 0.308042 36.859893 35.627725 36.162771 3.562891 37.613953 0.056893 30.735430 0.088177 43.752965 -0.053302 0 0

Train & test Dataset for Multistep Process

In [38]:
# Get features and target
X_value = pd.DataFrame(dataset_final.iloc[:, :])
y_value = pd.DataFrame(dataset_final.iloc[:, 3])
In [39]:
y_value.head(5)
Out[39]:
Close
2017-07-03 35.875000
2017-07-05 36.022499
2017-07-06 35.682499
2017-07-07 36.044998
2017-07-10 36.264999
In [40]:
# Normalized the data
X_scaler = MinMaxScaler(feature_range=(-1, 1))
y_scaler = MinMaxScaler(feature_range=(-1, 1))
X_scaler.fit(X_value)
y_scaler.fit(y_value)
Out[40]:
MinMaxScaler(feature_range=(-1, 1))
In [41]:
X_scale_dataset = X_scaler.fit_transform(X_value)
y_scale_dataset = y_scaler.fit_transform(y_value)
In [42]:
X_scale_dataset.shape, y_scale_dataset.shape,
Out[42]:
((1080, 22), (1080, 1))
In [43]:
X_value.shape[1]
Out[43]:
22

N Steps Definition

In [44]:
n_steps_in = 3
n_features = X_value.shape[1] #19 features
n_steps_out = 1
In [45]:
# Reshape the data
'''Set the data input steps and output steps, 
    we use 30 days data to predict 1 day price here, 
    reshape it to (None, input_step, number of features) used for LSTM input'''
# Get X/y dataset
def get_X_y(X_data, y_data):
    X = list()
    y = list()
    yc = list()

    length = len(X_data)
    for i in range(0, length, 1):
        # pdb.set_trace()
        X_value = X_data[i: i + n_steps_in][:, :]
        # print('[',i,': ',i,' + ',n_steps_in,'][:, :]')
        y_value = y_data[i + n_steps_in: i + (n_steps_in + n_steps_out)][:, 0]
        # print('[',i,' + ',n_steps_in,': ',i,' + (',n_steps_in,' + ',n_steps_out,')][:, 0]')
        yc_value = y_data[i: i + n_steps_in][:, :]
        if len(X_value) == 3 and len(y_value) == 1:
            X.append(X_value)
            y.append(y_value)
            yc.append(yc_value)

    return np.array(X), np.array(y), np.array(yc)
In [46]:
# get the train test predict index
def predict_index(dataset, X_train, n_steps_in, n_steps_out):

    # get the predict data (remove the in_steps days)
    train_predict_index = dataset.iloc[n_steps_in : X_train.shape[0] + n_steps_in + n_steps_out - 1, :].index
    test_predict_index = dataset.iloc[X_train.shape[0] + n_steps_in:, :].index

    return train_predict_index, test_predict_index
In [47]:
def mean_absolute_percentage_error(actual, prediction):
    actual = pd.Series(actual)
    prediction = pd.Series(prediction)
    return 100 * np.mean(np.abs((actual - prediction))/actual)
In [48]:
# Split train/test dataset
def split_train_test(data):
    train_size = round(len(X) * 0.75)
    data_train = data[0:train_size]
    data_test = data[train_size:]
    return data_train, data_test
In [49]:
# Get data and check shape
X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
# pdb.set_trace()
X_train, X_test, = split_train_test(X)
y_train, y_test, = split_train_test(y)
yc_train, yc_test, = split_train_test(yc)
index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
In [50]:
# %% --------------------------------------- Save dataset -----------------------------------------------------------------
print('X shape: ', X.shape)
print('y shape: ', y.shape)
print('X_train shape: ', X_train.shape)
print('y_train shape: ', y_train.shape)
print('y_c_train shape: ', yc_train.shape)
print('X_test shape: ', X_test.shape)
print('y_test shape: ', y_test.shape)
print('y_c_test shape: ', yc_test.shape)
print('index_train shape:', index_train.shape)
print('index_test shape:', index_test.shape)

X shape:  (1077, 3, 22)
y shape:  (1077, 1)
X_train shape:  (808, 3, 22)
y_train shape:  (808, 1)
y_c_train shape:  (808, 3, 1)
X_test shape:  (269, 3, 22)
y_test shape:  (269, 1)
y_c_test shape:  (269, 3, 1)
index_train shape: (808,)
index_test shape: (269,)
In [51]:
output_dim = y_train.shape[1]
output_dim
Out[51]:
1
In [52]:
df = dataset_final.copy()
In [53]:
df.rename(columns={'Date':'date','Open':'open','Low':'low','Close':'close','Volume':'volume','High':'high'}, inplace = True)
df.reset_index(drop=True,inplace=True)
In [54]:
df.head(1)
Out[54]:
open high low close Adj Close volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp COVID positiveIncrease COVID deathIncrease
0 36.220001 36.325001 35.775002 35.875 34.054882 57111200.0 36.173571 36.751904 0.303356 0.96052 38.672945 34.830864 35.924548 3.55177 38.458011 0.046984 29.704545 0.102857 43.304973 -0.053955 0 0
In [55]:
# df.drop(['volume', 'MACD','20SD','logmomentum','absolute of 3 comp','angle of 3 comp','absolute of 6 comp','angle of 6 comp','absolute of 9 comp','angle of 9 comp'], axis='columns', inplace=True) # only keep columns that can help as residuals in Arima Hybrid
In [56]:
df.head(1)
Out[56]:
open high low close Adj Close volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp COVID positiveIncrease COVID deathIncrease
0 36.220001 36.325001 35.775002 35.875 34.054882 57111200.0 36.173571 36.751904 0.303356 0.96052 38.672945 34.830864 35.924548 3.55177 38.458011 0.046984 29.704545 0.102857 43.304973 -0.053955 0 0

Train & Test Length

In [57]:
test_len = len(X_test)
In [58]:
train_len = len(X_train )
In [59]:
test_len, train_len
Out[59]:
(269, 808)

Kurtosis Review

In [60]:
# Initialize moving averages from Ta-Lib, store functions in dictionary
# talib_moving_averages = ['SMA', 'EMA', 'WMA', 'DEMA', 'KAMA', 'MIDPOINT', 'MIDPRICE', 'T3', 'TEMA', 'TRIMA'] remove midprice due to outputbeing univariate
talib_moving_averages = ['SMA', 'EMA', 'WMA', 'DEMA', 'KAMA', 'MIDPOINT',  'T3', 'TEMA', 'TRIMA'] 
functions = {}
for ma in talib_moving_averages:
      functions[ma] = abstract.Function(ma)

    # Determine kurtosis "K" values for MA period 4-30
kurtosis_results = {'period': []}
for i in range(4, 100): # 100
  kurtosis_results['period'].append(i)
  for ma in talib_moving_averages:
              # Run moving average, remove last N days (used later for test data set), trim MA result to last 30 days
              ma_output = functions[ma](df[:-test_len], i).tail(14)
              # Determine kurtosis "K" value
              k = kurtosis(ma_output, fisher=False)
              # add to dictionary
              if ma not in kurtosis_results.keys():
                  kurtosis_results[ma] = []
              kurtosis_results[ma].append(k)

kurtosis_results = pd.DataFrame(kurtosis_results)
kurtosis_results.to_csv('kurtosis_results.csv')
In [61]:
kurtosis_results.head(5)
Out[61]:
period SMA EMA WMA DEMA KAMA MIDPOINT T3 TEMA TRIMA
0 4 2.272452 2.652772 2.896972 3.800351 2.299585 2.171369 1.978458 4.609342 2.411225
1 5 1.839451 2.355815 2.481058 3.327525 1.841282 1.826597 1.640277 4.262302 1.994382
2 6 1.583886 2.159532 2.194320 2.945924 1.536136 1.605787 1.510972 3.878845 1.679710
3 7 1.461290 2.026758 1.990629 2.651927 1.506197 1.558096 1.514015 3.510432 1.486348
4 8 1.447516 1.935302 1.853935 2.429648 1.509566 1.621595 1.601580 3.184123 1.373337

Optimized periods

In [62]:
# Determine period with K closest to 3 +/-5%
optimized_period = {}
# https://pypi.org/project/TA-Lib/ determines the type of moving average to use
# https://pandas.pydata.org/pandas-docs/version/0.17.0/generated/pandas.DataFrame.at.html#pandas.DataFrame.at
for ma in talib_moving_averages:
        difference = np.abs(kurtosis_results[ma] - 3)
        df_arimahyb = pd.DataFrame({'difference': difference, 'period': kurtosis_results['period']})
        df_arimahyb = df_arimahyb.sort_values(by=['difference'], ascending=True).reset_index(drop=True)
        if df_arimahyb.at[0, 'difference'] < 3 * 0.05:
            optimized_period[ma] = df_arimahyb.at[0, 'period']
        else:
            print(ma + ' is not viable, best K greater or less than 3 +/-5%')

print('\nOptimized periods:', optimized_period)

TRIMA is not viable, best K greater or less than 3 +/-5%

Optimized periods: {'SMA': 17, 'EMA': 51, 'WMA': 49, 'DEMA': 89, 'KAMA': 18, 'MIDPOINT': 14, 'T3': 19, 'TEMA': 9}
In [63]:
optimized_period
Out[63]:
{'DEMA': 89,
 'EMA': 51,
 'KAMA': 18,
 'MIDPOINT': 14,
 'SMA': 17,
 'T3': 19,
 'TEMA': 9,
 'WMA': 49}

Simulation Keys

In [64]:
simulation = {}
for ma in optimized_period:
        print(ma)
        print(functions[ma])
        print ( int( optimized_period[ma]))
        # if ma in ['EMA','WMA','DEMA','KAMA','MIDPOINT']:
        #   print(ma)
        low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
        low_vol = low_vol.fillna(0)
        high_vol = pd.DataFrame()
        df2 = df.copy()
        for i in df2.columns:
          if i in low_vol.columns:
            high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9
In [65]:
low_vol.tail(20)
Out[65]:
open high low close Adj Close volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp COVID positiveIncrease COVID deathIncrease
1060 140.200839 141.942909 138.524500 140.171495 139.966842 8.852448e+07 142.165478 146.699207 1.815578 4.572948 155.845103 137.553312 140.365562 4.935800 105.739092 -0.047411 125.318767 -0.018291 140.471430 -0.008749 109077.158389 1731.777447
1061 139.425914 141.705469 138.035200 140.698014 140.492650 8.620711e+07 141.528981 145.978836 2.115887 4.189393 154.357621 137.600050 140.587196 4.939545 105.263514 -0.048037 124.464999 -0.019222 139.335869 -0.009472 102841.290470 1754.266015
1062 140.773058 142.636405 139.932338 141.733666 141.526843 7.421445e+07 141.294887 145.298477 2.211018 3.647690 152.593858 138.003097 141.351509 4.946870 104.786174 -0.048658 123.598217 -0.020150 138.164839 -0.010188 105557.460315 2130.717759
1063 142.179695 143.266994 141.127848 142.249061 142.041527 6.519616e+07 141.224295 144.665584 2.093072 3.241276 151.148137 138.183031 141.949877 4.950518 104.307114 -0.049275 122.718682 -0.021074 136.959041 -0.010898 102639.580150 2301.041924
1064 142.253947 144.008334 141.546689 142.555532 142.347589 6.254214e+07 141.336839 144.184381 1.988881 2.884864 149.954110 138.414652 142.353647 4.952685 103.826381 -0.049886 121.826667 -0.021994 135.719217 -0.011600 69581.281276 1416.274721
1065 142.782738 143.732491 141.438660 142.125353 141.918068 6.542511e+07 141.385297 143.758659 1.774804 2.626682 149.012024 138.505294 142.201451 4.949632 103.344020 -0.050491 120.922446 -0.022909 134.446150 -0.012293 82284.124854 1213.050329
1066 142.153085 142.656915 140.466684 141.564232 141.357788 7.040262e+07 141.585336 143.387397 1.634667 2.376817 148.141030 138.633764 141.776638 4.945637 102.860075 -0.051092 120.006305 -0.023818 133.140665 -0.012977 91985.728638 1671.446790
1067 142.177201 143.194327 140.977156 142.610382 142.402435 6.948112e+07 141.933749 143.094536 1.573317 2.074153 147.242842 138.946230 142.332468 4.953023 102.374593 -0.051687 119.078535 -0.024722 131.803627 -0.013650 105946.749025 2401.564322
1068 143.009006 144.052615 142.286776 143.812497 143.602819 6.805244e+07 142.378675 142.879716 1.473333 1.874158 146.628032 139.131400 143.319154 4.961467 101.887619 -0.052275 118.139433 -0.025618 130.435938 -0.014311 97749.622599 2337.714304
1069 143.380322 145.547752 142.940349 145.397429 145.185452 7.592729e+07 142.902069 142.813890 1.447641 1.844159 146.502207 139.125573 144.704671 4.972505 101.399198 -0.052858 117.189304 -0.026508 129.038540 -0.014959 65512.021173 1450.883588
1070 145.337970 147.615882 144.980528 147.444584 147.229635 7.653090e+07 143.644287 142.961273 1.284466 2.010227 146.981728 138.940819 146.531280 4.986604 100.909377 -0.053435 116.228458 -0.027389 127.612408 -0.015592 81208.790926 1562.998080
1071 147.375283 149.163050 146.995423 148.921380 148.704294 6.811986e+07 144.553694 143.236380 0.961952 2.270386 147.777152 138.695607 148.124680 4.996737 100.418203 -0.054006 115.257214 -0.028261 126.158555 -0.016211 80097.040341 1799.104627
1072 148.656821 150.010875 148.071943 149.870634 149.652170 6.425222e+07 145.660163 143.530869 0.589081 2.556352 148.643574 138.418164 149.288649 5.003230 99.925720 -0.054570 114.275894 -0.029124 124.678027 -0.016812 84773.597081 2474.891188
1073 149.806550 150.715254 149.026204 149.977942 149.759331 6.069918e+07 146.862121 143.785380 0.135134 2.805932 149.397244 138.173516 149.748178 5.003989 99.431976 -0.055128 113.284828 -0.029977 123.171903 -0.017396 81822.656493 2309.512985
1074 149.937482 150.666013 149.022091 149.911667 149.693162 5.465321e+07 147.905162 144.001463 -0.245163 3.045742 150.092948 137.909978 149.857170 5.003545 98.937018 -0.055679 112.284350 -0.030820 121.641290 -0.017961 50071.065843 1328.997652
1075 150.228161 151.254072 149.586503 150.104281 149.885502 5.602702e+07 148.803988 144.237215 -0.571069 3.270011 150.777237 137.697192 150.021910 5.004835 98.440892 -0.056223 111.274800 -0.031650 120.087330 -0.018506 78497.995262 1318.889721
1076 150.328251 150.997797 149.591175 149.912656 149.694163 5.484778e+07 149.449021 144.548659 -0.850904 3.458615 151.465890 137.631428 149.949074 5.003520 97.943645 -0.056759 110.256524 -0.032469 118.511190 -0.019029 73847.766335 1393.610487
1077 150.525566 152.430694 150.099878 151.531571 151.310718 7.580033e+07 150.032876 144.967153 -0.975625 3.719924 152.407001 137.527305 151.004072 5.014296 97.445324 -0.057289 109.229873 -0.033274 116.914063 -0.019528 86701.762012 1676.051703
1078 149.301052 151.688142 148.723104 151.137179 150.916905 1.012990e+08 150.349418 145.413317 -0.891585 3.905336 153.223988 137.602646 151.092810 5.011652 96.945977 -0.057811 108.195203 -0.034066 115.297171 -0.020004 83539.187040 1748.759489
1079 149.321425 151.018197 148.455004 150.396057 150.176865 9.262134e+07 150.424479 145.823313 -0.852689 3.878291 153.579894 138.066731 150.628308 5.006660 96.445650 -0.058325 107.152874 -0.034844 113.661756 -0.020453 58706.570197 1004.292073
In [66]:
high_vol.head(10)
Out[66]:
open high low close Adj Close volume MA7 MA21 MACD 20SD upper_band lower_band EMA logmomentum absolute of 3 comp angle of 3 comp absolute of 6 comp angle of 6 comp absolute of 9 comp angle of 9 comp COVID positiveIncrease COVID deathIncrease
0 36.220001 36.325001 35.775002 35.875000 34.054882 57111200.0 36.173571 36.751904 0.303356 0.960520 38.672945 34.830864 35.924548 3.551770 38.458011 0.046984 29.704545 0.102857 43.304973 -0.053955 0.0 0.0
1 35.922501 36.197498 35.680000 36.022499 34.194897 86278400.0 36.095357 36.634762 0.328795 0.852735 38.340231 34.929292 35.989849 3.555991 38.240991 0.049445 29.954520 0.099254 43.438321 -0.053936 0.0 0.0
2 35.755001 35.875000 35.602501 35.682499 33.872143 96515200.0 35.984999 36.495238 0.346702 0.677629 37.850495 35.139980 35.784949 3.546235 38.027974 0.051918 30.209839 0.095602 43.557403 -0.053820 0.0 0.0
3 35.724998 36.187500 35.724998 36.044998 34.216255 76806800.0 36.001071 36.362023 0.387422 0.387634 37.137291 35.586756 35.958315 3.556633 37.818962 0.054401 30.470232 0.091907 43.662260 -0.053608 0.0 0.0
4 36.027500 36.487499 35.842499 36.264999 34.425095 84362400.0 35.973571 36.243809 0.388315 0.308042 36.859893 35.627725 36.162771 3.562891 37.613953 0.056893 30.735430 0.088177 43.752965 -0.053302 0.0 0.0
5 36.182499 36.462502 36.095001 36.382500 34.536625 79127200.0 36.039642 36.202738 0.372153 0.308860 36.820458 35.585018 36.309257 3.566217 37.412947 0.059392 31.005161 0.084416 43.829622 -0.052901 0.0 0.0
6 36.467499 36.544998 36.205002 36.435001 34.586472 99538000.0 36.101071 36.206547 0.317572 0.295861 36.798268 35.614826 36.393086 3.567700 37.215939 0.061899 31.279154 0.080632 43.892360 -0.052406 0.0 0.0
7 36.375000 37.122501 36.360001 36.942501 35.068211 100797600.0 36.253571 36.220595 0.322643 0.340687 36.901969 35.539221 36.759363 3.581920 37.022928 0.064410 31.557136 0.076830 43.941338 -0.051818 0.0 0.0
8 36.992500 37.332500 36.832500 37.259998 35.369610 80528400.0 36.430357 36.266785 0.257925 0.410484 37.087753 35.445818 37.093120 3.590715 36.833908 0.066926 31.838833 0.073014 43.976744 -0.051137 0.0 0.0
9 37.205002 37.724998 37.142502 37.389999 35.493000 95174000.0 36.674285 36.329523 0.184267 0.445597 37.220717 35.438330 37.291039 3.594294 36.648875 0.069445 32.123972 0.069192 43.998789 -0.050365 0.0 0.0

Common Functions

In [73]:
def get_arima(dataframe,original_data, train_len, test_len):
    # prepare train and test data
    X_value = pd.DataFrame(dataframe.iloc[:, :])
    y_value = pd.DataFrame(dataframe.iloc[:, 3])
    X_train, X_test = split_train_test(X_value)
    y_train, y_test = split_train_test(y_value)
    yc_train,yc_test = split_train_test(original_data)
    # y_train_ = y_train['close'].to_list()
    # y_test_ = y_test['close'].to_list()
    yc = yc_test.values.tolist()
    y_train_list = y_train['close'].values.tolist() 
    y_test_list = y_test['close'].values.tolist()                                           
      
    # Initialize model
    model = auto_arima(y_train_list,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
                  suppress_warnings=True,stepwise=True,seasonal=True)
    print(model.summary())
        # Determine model parameters
    model.fit(y_train_list,disp= 0)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

        # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
            model = pmdarima.ARIMA(order=order)
            model.fit(y_train_list,disp= 0)
            # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')
            prediction.append(model.predict()[0])
            y_train_list.append(y_test_list[i])

    # Generate error data
    mse = mean_squared_error(yc_test, prediction)
    rmse = mse ** 0.5
    # mape = mean_absolute_percentage_error(pd.Series(yc_test).values.tolist(), pd.Series(predictionte).values.tolist() )
    mae = mean_absolute_error(pd.Series(yc_test).values.tolist() , pd.Series(prediction).values.tolist() )
    return yc, prediction, mse, rmse, mae
In [74]:
def plot_train(simulation,SIM):
  train_predict_index = np.load("index_train_appl.npy", allow_pickle=True)#Dates for train data

  predict_result = pd.DataFrame()
  for i in range(len(simulation[SIM]['final_tr']['prediction'])):
          y_predict = pd.DataFrame(simulation[SIM]['final_tr']['prediction'][i], columns=["predicted_price"],
                                  index=train_predict_index[i:i + output_dim])
          predict_result = pd.concat([predict_result, y_predict], axis=1, sort=False)
          
          #This is a dataframe with each column containing the predicted daily closing price
  real_price = pd.DataFrame()
  for i in range(len(simulation[SIM]['final_tr']['original'])):
          y_train = pd.DataFrame(simulation[SIM]['final_tr']['original'][i], columns=["real_price"],
                                index=train_predict_index[i:i + output_dim])
          real_price = pd.concat([real_price, y_train], axis=1, sort=False)  #This is a dataframe with each column containing the real daily closing price

  predict_result['predicted_mean'] = predict_result.mean(axis=1)#Adding a column with the daily predicted closing price value
  real_price['real_mean'] = real_price.mean(axis=1)#Adding a column with the daily real closing price value
      #
      # Plot the predicted result
  plt.figure(figsize=(16, 8))
  plt.plot(real_price["real_mean"])
  plt.plot(predict_result["predicted_mean"], color='r')
  plt.xlabel("Date")
  plt.ylabel("Stock price")
  plt.legend(("Real price", "Predicted price"), loc="upper left", fontsize=16)
  plt.title(f"The result of Training for Hybrid Arima LSTM with MA - {SIM} : {fileimg}",fontsize=20)
  sf = fileimg+'_'+SIM+'Train Hybrid Arima LSTM Pred Out.png'
  plt.savefig(sf,dpi='figure')
  plt.show()

      # Calculate RMSE
  predicted = predict_result["predicted_mean"]
  real = real_price["real_mean"]
  RMSE = np.sqrt(mean_squared_error(predicted, real))
  MSE = mean_squared_error(predicted, real)
  MAE = mean_absolute_error(predicted, real)
  print(f"----- Train RMSE for {SIM} -----", RMSE)
  print(f"----- Train_MSE_LSTM for {SIM} -----", MSE)
  print(f"----- Train MAE LSTM for {SIM} -----", MAE)
In [75]:
def plot_test(simulation, SIM):
  test_predict_index = np.load("index_test_appl.npy", allow_pickle=True)#Dates for train data

      # rescaled_real_y = y_scaler.inverse_transform(y_train)#Real closing price data
      # rescaled_predicted_y = y_scaler.inverse_transform(train_yhat)#Predicted closing price data

  predict_result = pd.DataFrame()
  for i in range(len(simulation[SIM]['final']['prediction'])):
          y_predict = pd.DataFrame(simulation[SIM]['final']['prediction'][i], columns=["predicted_price"],
                                  index=test_predict_index[i:i + output_dim])
          predict_result = pd.concat([predict_result, y_predict], axis=1, sort=False)#This is a dataframe with each column containing the predicted daily closing price
      #
  real_price = pd.DataFrame()
  for i in range(len(simulation[SIM]['final']['original'])):
          y_train = pd.DataFrame(simulation[SIM]['final']['original'][i], columns=["real_price"],
                                index=test_predict_index[i:i + output_dim])
          real_price = pd.concat([real_price, y_train], axis=1, sort=False)#This is a dataframe with each column containing the real daily closing price

  predict_result['predicted_mean'] = predict_result.mean(axis=1)#Adding a column with the daily predicted closing price value
  real_price['real_mean'] = real_price.mean(axis=1)#Adding a column with the daily real closing price value
      #
      # Plot the predicted result
  plt.figure(figsize=(16, 8))
  plt.plot(real_price["real_mean"])
  plt.plot(predict_result["predicted_mean"], color='r')
  plt.xlabel("Date")
  plt.ylabel("Stock price")
  plt.legend(("Real price", "Predicted price"), loc="upper left", fontsize=16)
  plt.title(f"The result of Testing for Hybrid Arima LSTM with MA - {SIM} : {fileimg}",fontsize=20)
  sf = fileimg+'_'+SIM+'Test Hybrid Arima LSTM Pred Out.png'
  plt.savefig(sf,dpi='figure')
  plt.show()

      # Calculate RMSE
  predicted = predict_result["predicted_mean"]
  real = real_price["real_mean"]
  RMSE = np.sqrt(mean_squared_error(predicted, real))
  MSE = mean_squared_error(predicted, real)
  MAE = mean_absolute_error(predicted, real)
  print(f"----- Test RMSE for {SIM}-----", RMSE)
  print(f"----- Test_MSE_LSTM for {SIM}-----", MSE)
  print(f"----- Test_MAE_LSTM for {SIM}-----", MAE)
In [76]:
def plot_train_high(simulation, SIM):
  train_predict_index = np.load("index_test_appl.npy", allow_pickle=True)#Dates for train data

  predict_result = pd.DataFrame()
  for i in range(len(simulation[SIM]['high_vol']['prediction'])):
          y_predict = pd.DataFrame(simulation[SIM]['high_vol']['prediction'][i], columns=["predicted_price"],
                                  index=train_predict_index[i:i + output_dim])
          predict_result = pd.concat([predict_result, y_predict], axis=1, sort=False)
          
          #This is a dataframe with each column containing the predicted daily closing price
  real_price = pd.DataFrame()
  for i in range(len(simulation[SIM]['high_vol']['original'])):
          y_train = pd.DataFrame(simulation[SIM]['high_vol']['original'][i], columns=["real_price"],
                                index=train_predict_index[i:i + output_dim])
          real_price = pd.concat([real_price, y_train], axis=1, sort=False)  #This is a dataframe with each column containing the real daily closing price

  predict_result['predicted_mean'] = predict_result.mean(axis=1)#Adding a column with the daily predicted closing price value
  real_price['real_mean'] = real_price.mean(axis=1)#Adding a column with the daily real closing price value
      #
      # Plot the predicted result
  plt.figure(figsize=(16, 8))
  plt.plot(real_price["real_mean"])
  plt.plot(predict_result["predicted_mean"], color='r')
  plt.xlabel("Date")
  plt.ylabel("Stock price")
  plt.legend(("Real price", "Predicted price"), loc="upper left", fontsize=16)
  plt.title(f"The result of Training for {SIM}", fontsize=20)
  plt.show()

      # Calculate RMSE
  predicted = predict_result["predicted_mean"]
  real = real_price["real_mean"]
  RMSE = np.sqrt(mean_squared_error(predicted, real))
  MSE = mean_squared_error(predicted, real)
  MAE = mean_absolute_error(predicted, real)
  print(f"----- Individual LSTM RMSE for {SIM} -----", RMSE)
  print(f"----- Individual LSTM_MSE_LSTM for {SIM} -----", MSE)
  print(f"----- Individual LSTM MAE LSTM for {SIM} -----", MAE)
In [77]:
def plot_train_low(simulation , SIM):
  train_predict_index = np.load("index_test_appl.npy", allow_pickle=True)#Dates for train data

  predict_result = pd.DataFrame()
  for i in range(len(simulation[SIM]['low_vol']['prediction'])):
          y_predict = pd.DataFrame(simulation[SIM]['low_vol']['prediction'][i], columns=["predicted_price"],
                                  index=train_predict_index[i:i + output_dim])
          predict_result = pd.concat([predict_result, y_predict], axis=1, sort=False)
          
          #This is a dataframe with each column containing the predicted daily closing price
  real_price = pd.DataFrame()
  for i in range(len(simulation[SIM]['low_vol']['original'])):
          y_train = pd.DataFrame(simulation[SIM]['low_vol']['original'][i], columns=["real_price"],
                                index=train_predict_index[i:i + output_dim])
          real_price = pd.concat([real_price, y_train], axis=1, sort=False)  #This is a dataframe with each column containing the real daily closing price

  predict_result['predicted_mean'] = predict_result.mean(axis=1)#Adding a column with the daily predicted closing price value
  real_price['real_mean'] = real_price.mean(axis=1)#Adding a column with the daily real closing price value
      #
      # Plot the predicted result
  plt.figure(figsize=(16, 8))
  plt.plot(real_price["real_mean"])
  plt.plot(predict_result["predicted_mean"], color='r')
  plt.xlabel("Date")
  plt.ylabel("Stock price")
  plt.legend(("Real price", "Predicted price"), loc="upper left", fontsize=16)
  plt.title(f"The result of Training for {SIM}", fontsize=20)
  plt.show()

      # Calculate RMSE
  predicted = predict_result["predicted_mean"]
  real = real_price["real_mean"]
  RMSE = np.sqrt(mean_squared_error(predicted, real))
  MSE = mean_squared_error(predicted, real)
  MAE = mean_absolute_error(predicted, real)
  print(f"-----Arima RMSE for {SIM} -----", RMSE)
  print(f"----- Arima MSE for {SIM} -----", MSE)
  print(f"----- Arima MAE for {SIM} -----", MAE)
In [78]:
import os
os.getcwd()
Out[78]:
'/content/drive/.shortcut-targets-by-id/1IaGjVBlTspxI2CHSrxfYnaiYvsaG0pHs/Stock price prediction/Archana - LSTM Hybrid/Outputs/Covid'

Univariate Arima Multistep MutiVariate LSTM Hybrid Model Experiment 1

In [ ]:
def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    model = Sequential()
    model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    model.add(Dense(units=64,activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(units=output_dim))
    model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    ## Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()


    # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 3
    # define custom activation
    # cts().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te
In [ ]:
if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation1 = {}
    imgfile = 'Experiment1'
    for ma in optimized_period:
              print(ma)
              print(functions[ma])
              print ( int( optimized_period[ma]))
            # if ma == 'SMA':
              low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
              low_vol = low_vol.fillna(0)
              low_vol_data = df['close']
              high_vol = pd.DataFrame()
              df2 = df.copy()
              for i in df2.columns:
                if i in low_vol.columns:
                  high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
              high_vol_data = df['close']
              ## *****************************************************
              # Generate ARIMA and LSTM predictions
              print('\nWorking on ' + ma + ' predictions')
              try:
                print('parameters used : ', train_len, test_len)
                low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima(low_vol,low_vol_data, train_len, test_len)
              except:
                  print('ARIMA error, skipping to next MA type')
                  continue
              Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
              final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
              mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
              rmse_ftr = mse_ftr ** 0.5
              mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
              mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

              final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
              mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
              rmse = mse ** 0.5
              mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              # Generate prediction accuracy
              actual = df['close'].tail(test_len).values
              result_1 = []
              result_2 = []
              for i in range(1, len(final_prediction)):
                  # Compare prediction to previous close price
                  if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                      result_1.append(1)
                  elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                      result_1.append(1)
                  else:
                      result_1.append(0)

                  # Compare prediction to previous prediction
                  if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                      result_2.append(1)
                  elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                      result_2.append(1)
                  else:
                      result_2.append(0)

              accuracy_1 = np.mean(result_1)
              accuracy_2 = np.mean(result_2)

              simulation1[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                            'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                            'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                            'rmse': rmse_ftr, 'mae' : mae_ftr},
                                'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                          'rmse': rmse, 'mae': mae },
                                'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

              # save simulation data here as checkpoint
              with open('simulation1_data.json', 'w') as fp:
                  json.dump(simulation1, fp)

              for ma in simulation1.keys():
                  print('\n' + ma)
                  print('Prediction vs Close:\t\t' + str(round(100*simulation1[ma]['accuracy']['prediction vs close'], 2))
                        + '% Accuracy')
                  print('Prediction vs Prediction:\t' + str(round(100*simulation1[ma]['accuracy']['prediction vs prediction'], 2))
                        + '% Accuracy')
                  print('MSE:\t', simulation1[ma]['final']['mse'],
                        '\nRMSE:\t', simulation1[ma]['final']['rmse'],
                        '\nMAPE:\t', simulation1[ma]['final']['mae'])#,
                        # '\nMAPE:\t', simulation[ma]['final']['mape'])
            # else:
            #   break
            # code you want to evaluate
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.48 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4157.020, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3687.148, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.15 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3458.651, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3322.133, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.53 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.58 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3324.133, Time=0.15 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.098 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1657.067
Date:                Sun, 12 Dec 2021   AIC                           3322.133
Time:                        13:04:15   BIC                           3340.897
Sample:                             0   HQIC                          3329.339
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1966      0.003   -387.226      0.000      -1.203      -1.191
ar.L2         -0.8952      0.006   -138.692      0.000      -0.908      -0.883
ar.L3         -0.3968      0.006    -68.284      0.000      -0.408      -0.385
sigma2         3.5858      0.017    214.535      0.000       3.553       3.619
===================================================================================
Ljung-Box (L1) (Q):                  14.47   Jarque-Bera (JB):           2428881.42
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       271.99
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.00968, saving model to LSTM1.h5
48/48 - 4s - loss: 0.2459 - val_loss: 0.0097 - lr: 0.0010 - 4s/epoch - 76ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.1711 - val_loss: 0.0231 - lr: 0.0010 - 512ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0984 - val_loss: 0.8944 - lr: 0.0010 - 524ms/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0525 - val_loss: 0.2835 - lr: 0.0010 - 522ms/epoch - 11ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0453 - val_loss: 0.1463 - lr: 0.0010 - 537ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0397 - val_loss: 0.2374 - lr: 0.0010 - 540ms/epoch - 11ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0449 - val_loss: 0.2185 - lr: 1.0000e-04 - 514ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0362 - val_loss: 0.2081 - lr: 1.0000e-04 - 506ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0368 - val_loss: 0.1951 - lr: 1.0000e-04 - 521ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0323 - val_loss: 0.1830 - lr: 1.0000e-04 - 538ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.00968
48/48 - 0s - loss: 0.0316 - val_loss: 0.1684 - lr: 1.0000e-04 - 484ms/epoch - 10ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0363 - val_loss: 0.1677 - lr: 1.0000e-05 - 533ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0316 - val_loss: 0.1674 - lr: 1.0000e-05 - 518ms/epoch - 11ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0410 - val_loss: 0.1672 - lr: 1.0000e-05 - 521ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0348 - val_loss: 0.1674 - lr: 1.0000e-05 - 537ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0348 - val_loss: 0.1667 - lr: 1.0000e-05 - 537ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0361 - val_loss: 0.1659 - lr: 1.0000e-05 - 506ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0313 - val_loss: 0.1648 - lr: 1.0000e-05 - 535ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0334 - val_loss: 0.1638 - lr: 1.0000e-05 - 532ms/epoch - 11ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00968
48/48 - 0s - loss: 0.0317 - val_loss: 0.1637 - lr: 1.0000e-05 - 489ms/epoch - 10ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00968
48/48 - 0s - loss: 0.0335 - val_loss: 0.1625 - lr: 1.0000e-05 - 461ms/epoch - 10ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0314 - val_loss: 0.1615 - lr: 1.0000e-05 - 522ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0340 - val_loss: 0.1611 - lr: 1.0000e-05 - 519ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0310 - val_loss: 0.1605 - lr: 1.0000e-05 - 541ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00968
48/48 - 0s - loss: 0.0308 - val_loss: 0.1598 - lr: 1.0000e-05 - 492ms/epoch - 10ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0314 - val_loss: 0.1590 - lr: 1.0000e-05 - 520ms/epoch - 11ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0334 - val_loss: 0.1581 - lr: 1.0000e-05 - 528ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0334 - val_loss: 0.1573 - lr: 1.0000e-05 - 532ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0334 - val_loss: 0.1563 - lr: 1.0000e-05 - 559ms/epoch - 12ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0348 - val_loss: 0.1552 - lr: 1.0000e-05 - 520ms/epoch - 11ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0293 - val_loss: 0.1544 - lr: 1.0000e-05 - 510ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0334 - val_loss: 0.1538 - lr: 1.0000e-05 - 537ms/epoch - 11ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0327 - val_loss: 0.1528 - lr: 1.0000e-05 - 536ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0316 - val_loss: 0.1520 - lr: 1.0000e-05 - 514ms/epoch - 11ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0332 - val_loss: 0.1510 - lr: 1.0000e-05 - 536ms/epoch - 11ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0340 - val_loss: 0.1503 - lr: 1.0000e-05 - 534ms/epoch - 11ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0313 - val_loss: 0.1495 - lr: 1.0000e-05 - 531ms/epoch - 11ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0306 - val_loss: 0.1499 - lr: 1.0000e-05 - 513ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0352 - val_loss: 0.1484 - lr: 1.0000e-05 - 516ms/epoch - 11ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0306 - val_loss: 0.1483 - lr: 1.0000e-05 - 509ms/epoch - 11ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0324 - val_loss: 0.1472 - lr: 1.0000e-05 - 506ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0311 - val_loss: 0.1472 - lr: 1.0000e-05 - 526ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0322 - val_loss: 0.1460 - lr: 1.0000e-05 - 553ms/epoch - 12ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0304 - val_loss: 0.1454 - lr: 1.0000e-05 - 509ms/epoch - 11ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0297 - val_loss: 0.1445 - lr: 1.0000e-05 - 541ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0301 - val_loss: 0.1447 - lr: 1.0000e-05 - 520ms/epoch - 11ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00968
48/48 - 0s - loss: 0.0348 - val_loss: 0.1438 - lr: 1.0000e-05 - 488ms/epoch - 10ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0347 - val_loss: 0.1434 - lr: 1.0000e-05 - 509ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0301 - val_loss: 0.1431 - lr: 1.0000e-05 - 533ms/epoch - 11ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0306 - val_loss: 0.1438 - lr: 1.0000e-05 - 538ms/epoch - 11ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00968
48/48 - 1s - loss: 0.0315 - val_loss: 0.1442 - lr: 1.0000e-05 - 509ms/epoch - 11ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 29.531169515594907 
RMSE:	 5.434258874547192 
MAPE:	 4.511922179897357
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4231.556, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3761.238, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.20 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3532.227, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3394.496, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.92 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.51 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3396.496, Time=0.26 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.451 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1693.248
Date:                Sun, 12 Dec 2021   AIC                           3394.496
Time:                        13:06:14   BIC                           3413.260
Sample:                             0   HQIC                          3401.702
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.569      0.000      -1.204      -1.192
ar.L2         -0.8976      0.006   -139.811      0.000      -0.910      -0.885
ar.L3         -0.3984      0.006    -68.662      0.000      -0.410      -0.387
sigma2         3.9230      0.018    215.372      0.000       3.887       3.959
===================================================================================
Ljung-Box (L1) (Q):                  14.54   Jarque-Bera (JB):           2462173.05
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.82
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_1 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_1 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.14983, saving model to LSTM1.h5
16/16 - 2s - loss: 0.2317 - val_loss: 0.1498 - lr: 0.0010 - 2s/epoch - 128ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.14983 to 0.11662, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0996 - val_loss: 0.1166 - lr: 0.0010 - 226ms/epoch - 14ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.11662
16/16 - 0s - loss: 0.0823 - val_loss: 0.3269 - lr: 0.0010 - 194ms/epoch - 12ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.11662
16/16 - 0s - loss: 0.0624 - val_loss: 0.1525 - lr: 0.0010 - 190ms/epoch - 12ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.11662 to 0.07705, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0569 - val_loss: 0.0770 - lr: 0.0010 - 194ms/epoch - 12ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.07705 to 0.07685, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0481 - val_loss: 0.0768 - lr: 0.0010 - 213ms/epoch - 13ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.07685 to 0.06080, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0399 - val_loss: 0.0608 - lr: 0.0010 - 211ms/epoch - 13ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.06080
16/16 - 0s - loss: 0.0392 - val_loss: 0.0633 - lr: 0.0010 - 185ms/epoch - 12ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.06080 to 0.05583, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0385 - val_loss: 0.0558 - lr: 0.0010 - 218ms/epoch - 14ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05583
16/16 - 0s - loss: 0.0403 - val_loss: 0.0655 - lr: 0.0010 - 194ms/epoch - 12ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.05583 to 0.05034, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0368 - val_loss: 0.0503 - lr: 0.0010 - 239ms/epoch - 15ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05034
16/16 - 0s - loss: 0.0384 - val_loss: 0.0756 - lr: 0.0010 - 187ms/epoch - 12ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.05034 to 0.04115, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0379 - val_loss: 0.0411 - lr: 0.0010 - 201ms/epoch - 13ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04115
16/16 - 0s - loss: 0.0320 - val_loss: 0.0746 - lr: 0.0010 - 196ms/epoch - 12ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04115
16/16 - 0s - loss: 0.0340 - val_loss: 0.0445 - lr: 0.0010 - 188ms/epoch - 12ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.04115 to 0.03450, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0293 - val_loss: 0.0345 - lr: 0.0010 - 225ms/epoch - 14ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.03450
16/16 - 0s - loss: 0.0317 - val_loss: 0.0606 - lr: 0.0010 - 192ms/epoch - 12ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.03450 to 0.02444, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0298 - val_loss: 0.0244 - lr: 0.0010 - 220ms/epoch - 14ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.02444
16/16 - 0s - loss: 0.0308 - val_loss: 0.0328 - lr: 0.0010 - 194ms/epoch - 12ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.02444
16/16 - 0s - loss: 0.0302 - val_loss: 0.0269 - lr: 0.0010 - 186ms/epoch - 12ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.02444
16/16 - 0s - loss: 0.0350 - val_loss: 0.0861 - lr: 0.0010 - 177ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss improved from 0.02444 to 0.01752, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0342 - val_loss: 0.0175 - lr: 0.0010 - 218ms/epoch - 14ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01752
16/16 - 0s - loss: 0.0264 - val_loss: 0.0209 - lr: 0.0010 - 199ms/epoch - 12ms/step
Epoch 24/500

Epoch 00024: val_loss improved from 0.01752 to 0.01677, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0292 - val_loss: 0.0168 - lr: 0.0010 - 262ms/epoch - 16ms/step
Epoch 25/500

Epoch 00025: val_loss improved from 0.01677 to 0.01673, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0264 - val_loss: 0.0167 - lr: 0.0010 - 225ms/epoch - 14ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0247 - val_loss: 0.0485 - lr: 0.0010 - 197ms/epoch - 12ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0275 - val_loss: 0.0171 - lr: 0.0010 - 200ms/epoch - 12ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0250 - val_loss: 0.0807 - lr: 0.0010 - 186ms/epoch - 12ms/step
Epoch 29/500

Epoch 00029: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00029: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0218 - val_loss: 0.0172 - lr: 0.0010 - 192ms/epoch - 12ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0252 - val_loss: 0.0183 - lr: 1.0000e-04 - 189ms/epoch - 12ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0218 - val_loss: 0.0195 - lr: 1.0000e-04 - 201ms/epoch - 13ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0247 - val_loss: 0.0211 - lr: 1.0000e-04 - 188ms/epoch - 12ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0238 - val_loss: 0.0234 - lr: 1.0000e-04 - 194ms/epoch - 12ms/step
Epoch 34/500

Epoch 00034: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00034: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0238 - val_loss: 0.0247 - lr: 1.0000e-04 - 199ms/epoch - 12ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0197 - val_loss: 0.0247 - lr: 1.0000e-05 - 210ms/epoch - 13ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0242 - val_loss: 0.0247 - lr: 1.0000e-05 - 194ms/epoch - 12ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0213 - val_loss: 0.0246 - lr: 1.0000e-05 - 200ms/epoch - 12ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0230 - val_loss: 0.0246 - lr: 1.0000e-05 - 186ms/epoch - 12ms/step
Epoch 39/500

Epoch 00039: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00039: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0214 - val_loss: 0.0248 - lr: 1.0000e-05 - 192ms/epoch - 12ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0206 - val_loss: 0.0248 - lr: 1.0000e-05 - 193ms/epoch - 12ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0204 - val_loss: 0.0247 - lr: 1.0000e-05 - 202ms/epoch - 13ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0204 - val_loss: 0.0244 - lr: 1.0000e-05 - 198ms/epoch - 12ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0220 - val_loss: 0.0244 - lr: 1.0000e-05 - 202ms/epoch - 13ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0210 - val_loss: 0.0242 - lr: 1.0000e-05 - 180ms/epoch - 11ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0222 - val_loss: 0.0242 - lr: 1.0000e-05 - 176ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0219 - val_loss: 0.0242 - lr: 1.0000e-05 - 185ms/epoch - 12ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0223 - val_loss: 0.0242 - lr: 1.0000e-05 - 195ms/epoch - 12ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0214 - val_loss: 0.0240 - lr: 1.0000e-05 - 209ms/epoch - 13ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0214 - val_loss: 0.0240 - lr: 1.0000e-05 - 177ms/epoch - 11ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0214 - val_loss: 0.0241 - lr: 1.0000e-05 - 185ms/epoch - 12ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0205 - val_loss: 0.0244 - lr: 1.0000e-05 - 194ms/epoch - 12ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0210 - val_loss: 0.0243 - lr: 1.0000e-05 - 194ms/epoch - 12ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0233 - val_loss: 0.0243 - lr: 1.0000e-05 - 182ms/epoch - 11ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0221 - val_loss: 0.0243 - lr: 1.0000e-05 - 190ms/epoch - 12ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0213 - val_loss: 0.0243 - lr: 1.0000e-05 - 181ms/epoch - 11ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0231 - val_loss: 0.0242 - lr: 1.0000e-05 - 182ms/epoch - 11ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0221 - val_loss: 0.0241 - lr: 1.0000e-05 - 184ms/epoch - 11ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0222 - val_loss: 0.0242 - lr: 1.0000e-05 - 184ms/epoch - 11ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0214 - val_loss: 0.0242 - lr: 1.0000e-05 - 178ms/epoch - 11ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0208 - val_loss: 0.0243 - lr: 1.0000e-05 - 174ms/epoch - 11ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0194 - val_loss: 0.0246 - lr: 1.0000e-05 - 173ms/epoch - 11ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0206 - val_loss: 0.0249 - lr: 1.0000e-05 - 203ms/epoch - 13ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0221 - val_loss: 0.0247 - lr: 1.0000e-05 - 183ms/epoch - 11ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0205 - val_loss: 0.0246 - lr: 1.0000e-05 - 186ms/epoch - 12ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0214 - val_loss: 0.0246 - lr: 1.0000e-05 - 173ms/epoch - 11ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0213 - val_loss: 0.0245 - lr: 1.0000e-05 - 180ms/epoch - 11ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0227 - val_loss: 0.0247 - lr: 1.0000e-05 - 189ms/epoch - 12ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0226 - val_loss: 0.0248 - lr: 1.0000e-05 - 200ms/epoch - 13ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0214 - val_loss: 0.0248 - lr: 1.0000e-05 - 205ms/epoch - 13ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0208 - val_loss: 0.0248 - lr: 1.0000e-05 - 204ms/epoch - 13ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0195 - val_loss: 0.0248 - lr: 1.0000e-05 - 189ms/epoch - 12ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0209 - val_loss: 0.0250 - lr: 1.0000e-05 - 189ms/epoch - 12ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0220 - val_loss: 0.0251 - lr: 1.0000e-05 - 202ms/epoch - 13ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0205 - val_loss: 0.0251 - lr: 1.0000e-05 - 204ms/epoch - 13ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.01673
16/16 - 0s - loss: 0.0219 - val_loss: 0.0251 - lr: 1.0000e-05 - 186ms/epoch - 12ms/step
Epoch 00075: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 29.531169515594907 
RMSE:	 5.434258874547192 
MAPE:	 4.511922179897357

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 44.2948843329178 
RMSE:	 6.655440205795392 
MAPE:	 5.1903345685841265
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.39 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4264.089, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3793.930, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.18 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3564.923, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3427.258, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.92 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.35 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3429.258, Time=0.20 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.228 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1709.629
Date:                Sun, 12 Dec 2021   AIC                           3427.258
Time:                        13:07:43   BIC                           3446.021
Sample:                             0   HQIC                          3434.464
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1981      0.003   -389.386      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.699      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.737      0.000      -0.410      -0.387
sigma2         4.0860      0.019    215.311      0.000       4.049       4.123
===================================================================================
Ljung-Box (L1) (Q):                  14.57   Jarque-Bera (JB):           2460901.70
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.75
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_2 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_2 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.24073, saving model to LSTM1.h5
17/17 - 2s - loss: 0.3924 - val_loss: 0.2407 - lr: 0.0010 - 2s/epoch - 122ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.24073 to 0.21989, saving model to LSTM1.h5
17/17 - 0s - loss: 0.1053 - val_loss: 0.2199 - lr: 0.0010 - 229ms/epoch - 13ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.21989
17/17 - 0s - loss: 0.0880 - val_loss: 0.2684 - lr: 0.0010 - 207ms/epoch - 12ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.21989 to 0.10733, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0788 - val_loss: 0.1073 - lr: 0.0010 - 228ms/epoch - 13ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.10733 to 0.09092, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0505 - val_loss: 0.0909 - lr: 0.0010 - 224ms/epoch - 13ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.09092
17/17 - 0s - loss: 0.0526 - val_loss: 0.1424 - lr: 0.0010 - 213ms/epoch - 13ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.09092 to 0.08077, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0341 - val_loss: 0.0808 - lr: 0.0010 - 233ms/epoch - 14ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.08077
17/17 - 0s - loss: 0.0459 - val_loss: 0.0854 - lr: 0.0010 - 216ms/epoch - 13ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.08077 to 0.07047, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0303 - val_loss: 0.0705 - lr: 0.0010 - 232ms/epoch - 14ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.07047 to 0.05722, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0309 - val_loss: 0.0572 - lr: 0.0010 - 208ms/epoch - 12ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.05722
17/17 - 0s - loss: 0.0284 - val_loss: 0.0977 - lr: 0.0010 - 200ms/epoch - 12ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.05722 to 0.03317, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0355 - val_loss: 0.0332 - lr: 0.0010 - 227ms/epoch - 13ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0288 - val_loss: 0.1245 - lr: 0.0010 - 219ms/epoch - 13ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0268 - val_loss: 0.0359 - lr: 0.0010 - 194ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0426 - val_loss: 0.0501 - lr: 0.0010 - 181ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0438 - val_loss: 0.1058 - lr: 0.0010 - 198ms/epoch - 12ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00017: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0333 - val_loss: 0.0357 - lr: 0.0010 - 193ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0485 - val_loss: 0.0392 - lr: 1.0000e-04 - 195ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0312 - val_loss: 0.0395 - lr: 1.0000e-04 - 190ms/epoch - 11ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0303 - val_loss: 0.0414 - lr: 1.0000e-04 - 193ms/epoch - 11ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0271 - val_loss: 0.0419 - lr: 1.0000e-04 - 189ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00022: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0267 - val_loss: 0.0463 - lr: 1.0000e-04 - 198ms/epoch - 12ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0248 - val_loss: 0.0464 - lr: 1.0000e-05 - 183ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0259 - val_loss: 0.0466 - lr: 1.0000e-05 - 184ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0246 - val_loss: 0.0466 - lr: 1.0000e-05 - 184ms/epoch - 11ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0270 - val_loss: 0.0466 - lr: 1.0000e-05 - 187ms/epoch - 11ms/step
Epoch 27/500

Epoch 00027: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00027: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0230 - val_loss: 0.0472 - lr: 1.0000e-05 - 195ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0261 - val_loss: 0.0473 - lr: 1.0000e-05 - 199ms/epoch - 12ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0268 - val_loss: 0.0473 - lr: 1.0000e-05 - 205ms/epoch - 12ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0263 - val_loss: 0.0477 - lr: 1.0000e-05 - 188ms/epoch - 11ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0241 - val_loss: 0.0478 - lr: 1.0000e-05 - 190ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0250 - val_loss: 0.0478 - lr: 1.0000e-05 - 201ms/epoch - 12ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0241 - val_loss: 0.0480 - lr: 1.0000e-05 - 202ms/epoch - 12ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0244 - val_loss: 0.0483 - lr: 1.0000e-05 - 204ms/epoch - 12ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0266 - val_loss: 0.0488 - lr: 1.0000e-05 - 202ms/epoch - 12ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0255 - val_loss: 0.0492 - lr: 1.0000e-05 - 206ms/epoch - 12ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0261 - val_loss: 0.0497 - lr: 1.0000e-05 - 215ms/epoch - 13ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0266 - val_loss: 0.0500 - lr: 1.0000e-05 - 205ms/epoch - 12ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0252 - val_loss: 0.0499 - lr: 1.0000e-05 - 213ms/epoch - 13ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0278 - val_loss: 0.0502 - lr: 1.0000e-05 - 187ms/epoch - 11ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0247 - val_loss: 0.0502 - lr: 1.0000e-05 - 208ms/epoch - 12ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0237 - val_loss: 0.0502 - lr: 1.0000e-05 - 223ms/epoch - 13ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0253 - val_loss: 0.0500 - lr: 1.0000e-05 - 212ms/epoch - 12ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0255 - val_loss: 0.0497 - lr: 1.0000e-05 - 209ms/epoch - 12ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0250 - val_loss: 0.0498 - lr: 1.0000e-05 - 205ms/epoch - 12ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0261 - val_loss: 0.0498 - lr: 1.0000e-05 - 218ms/epoch - 13ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0271 - val_loss: 0.0497 - lr: 1.0000e-05 - 213ms/epoch - 13ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0245 - val_loss: 0.0498 - lr: 1.0000e-05 - 185ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0234 - val_loss: 0.0501 - lr: 1.0000e-05 - 208ms/epoch - 12ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0255 - val_loss: 0.0502 - lr: 1.0000e-05 - 202ms/epoch - 12ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0256 - val_loss: 0.0505 - lr: 1.0000e-05 - 199ms/epoch - 12ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0238 - val_loss: 0.0510 - lr: 1.0000e-05 - 190ms/epoch - 11ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0248 - val_loss: 0.0512 - lr: 1.0000e-05 - 208ms/epoch - 12ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0257 - val_loss: 0.0511 - lr: 1.0000e-05 - 191ms/epoch - 11ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0251 - val_loss: 0.0511 - lr: 1.0000e-05 - 188ms/epoch - 11ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0252 - val_loss: 0.0513 - lr: 1.0000e-05 - 199ms/epoch - 12ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0235 - val_loss: 0.0515 - lr: 1.0000e-05 - 205ms/epoch - 12ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0254 - val_loss: 0.0514 - lr: 1.0000e-05 - 203ms/epoch - 12ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0229 - val_loss: 0.0510 - lr: 1.0000e-05 - 198ms/epoch - 12ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0266 - val_loss: 0.0510 - lr: 1.0000e-05 - 211ms/epoch - 12ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0241 - val_loss: 0.0511 - lr: 1.0000e-05 - 192ms/epoch - 11ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.03317
17/17 - 0s - loss: 0.0247 - val_loss: 0.0511 - lr: 1.0000e-05 - 208ms/epoch - 12ms/step
Epoch 00062: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 29.531169515594907 
RMSE:	 5.434258874547192 
MAPE:	 4.511922179897357

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 44.2948843329178 
RMSE:	 6.655440205795392 
MAPE:	 5.1903345685841265

WMA
Prediction vs Close:		56.72% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 34.81241095672678 
RMSE:	 5.900204314829002 
MAPE:	 4.770935413189914
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.38 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4436.126, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3965.317, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.28 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3736.589, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3598.951, Time=0.11 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.20 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.74 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3600.951, Time=0.24 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.069 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1795.475
Date:                Sun, 12 Dec 2021   AIC                           3598.951
Time:                        13:09:08   BIC                           3617.714
Sample:                             0   HQIC                          3606.157
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1983      0.003   -389.581      0.000      -1.204      -1.192
ar.L2         -0.8973      0.006   -139.732      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.649      0.000      -0.410      -0.387
sigma2         5.0573      0.023    215.292      0.000       5.011       5.103
===================================================================================
Ljung-Box (L1) (Q):                  14.41   Jarque-Bera (JB):           2460553.80
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.89
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_3 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_3 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05104, saving model to LSTM1.h5
10/10 - 2s - loss: 0.8102 - val_loss: 0.0510 - lr: 0.0010 - 2s/epoch - 211ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.05104 to 0.04974, saving model to LSTM1.h5
10/10 - 0s - loss: 0.1873 - val_loss: 0.0497 - lr: 0.0010 - 152ms/epoch - 15ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0745 - val_loss: 0.2709 - lr: 0.0010 - 127ms/epoch - 13ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0673 - val_loss: 0.2236 - lr: 0.0010 - 135ms/epoch - 13ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0665 - val_loss: 0.1066 - lr: 0.0010 - 130ms/epoch - 13ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0543 - val_loss: 0.0958 - lr: 0.0010 - 124ms/epoch - 12ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0501 - val_loss: 0.1133 - lr: 0.0010 - 135ms/epoch - 14ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0470 - val_loss: 0.1117 - lr: 1.0000e-04 - 138ms/epoch - 14ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0453 - val_loss: 0.1132 - lr: 1.0000e-04 - 128ms/epoch - 13ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0413 - val_loss: 0.1125 - lr: 1.0000e-04 - 125ms/epoch - 12ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0441 - val_loss: 0.1106 - lr: 1.0000e-04 - 143ms/epoch - 14ms/step
Epoch 12/500

Epoch 00012: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00012: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0458 - val_loss: 0.1074 - lr: 1.0000e-04 - 148ms/epoch - 15ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0443 - val_loss: 0.1071 - lr: 1.0000e-05 - 126ms/epoch - 13ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0445 - val_loss: 0.1071 - lr: 1.0000e-05 - 136ms/epoch - 14ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0418 - val_loss: 0.1072 - lr: 1.0000e-05 - 137ms/epoch - 14ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0478 - val_loss: 0.1077 - lr: 1.0000e-05 - 131ms/epoch - 13ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00017: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0398 - val_loss: 0.1082 - lr: 1.0000e-05 - 140ms/epoch - 14ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0399 - val_loss: 0.1084 - lr: 1.0000e-05 - 143ms/epoch - 14ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0408 - val_loss: 0.1083 - lr: 1.0000e-05 - 140ms/epoch - 14ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0430 - val_loss: 0.1081 - lr: 1.0000e-05 - 131ms/epoch - 13ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0376 - val_loss: 0.1084 - lr: 1.0000e-05 - 133ms/epoch - 13ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0427 - val_loss: 0.1082 - lr: 1.0000e-05 - 145ms/epoch - 15ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0427 - val_loss: 0.1081 - lr: 1.0000e-05 - 142ms/epoch - 14ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0433 - val_loss: 0.1082 - lr: 1.0000e-05 - 136ms/epoch - 14ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0424 - val_loss: 0.1087 - lr: 1.0000e-05 - 138ms/epoch - 14ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0450 - val_loss: 0.1086 - lr: 1.0000e-05 - 143ms/epoch - 14ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0455 - val_loss: 0.1080 - lr: 1.0000e-05 - 136ms/epoch - 14ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0425 - val_loss: 0.1078 - lr: 1.0000e-05 - 148ms/epoch - 15ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0464 - val_loss: 0.1078 - lr: 1.0000e-05 - 125ms/epoch - 13ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0376 - val_loss: 0.1079 - lr: 1.0000e-05 - 134ms/epoch - 13ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0423 - val_loss: 0.1079 - lr: 1.0000e-05 - 133ms/epoch - 13ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0409 - val_loss: 0.1074 - lr: 1.0000e-05 - 134ms/epoch - 13ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0415 - val_loss: 0.1070 - lr: 1.0000e-05 - 140ms/epoch - 14ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0393 - val_loss: 0.1071 - lr: 1.0000e-05 - 130ms/epoch - 13ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0409 - val_loss: 0.1069 - lr: 1.0000e-05 - 129ms/epoch - 13ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0435 - val_loss: 0.1070 - lr: 1.0000e-05 - 136ms/epoch - 14ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0392 - val_loss: 0.1072 - lr: 1.0000e-05 - 128ms/epoch - 13ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0415 - val_loss: 0.1074 - lr: 1.0000e-05 - 130ms/epoch - 13ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0413 - val_loss: 0.1073 - lr: 1.0000e-05 - 134ms/epoch - 13ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0423 - val_loss: 0.1070 - lr: 1.0000e-05 - 136ms/epoch - 14ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0419 - val_loss: 0.1066 - lr: 1.0000e-05 - 140ms/epoch - 14ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0381 - val_loss: 0.1067 - lr: 1.0000e-05 - 135ms/epoch - 14ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0455 - val_loss: 0.1070 - lr: 1.0000e-05 - 122ms/epoch - 12ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0418 - val_loss: 0.1074 - lr: 1.0000e-05 - 132ms/epoch - 13ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0376 - val_loss: 0.1074 - lr: 1.0000e-05 - 138ms/epoch - 14ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0443 - val_loss: 0.1067 - lr: 1.0000e-05 - 134ms/epoch - 13ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0413 - val_loss: 0.1063 - lr: 1.0000e-05 - 138ms/epoch - 14ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0415 - val_loss: 0.1058 - lr: 1.0000e-05 - 143ms/epoch - 14ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0415 - val_loss: 0.1054 - lr: 1.0000e-05 - 135ms/epoch - 14ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0465 - val_loss: 0.1049 - lr: 1.0000e-05 - 147ms/epoch - 15ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0386 - val_loss: 0.1048 - lr: 1.0000e-05 - 137ms/epoch - 14ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.04974
10/10 - 0s - loss: 0.0408 - val_loss: 0.1050 - lr: 1.0000e-05 - 139ms/epoch - 14ms/step
Epoch 00052: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 29.531169515594907 
RMSE:	 5.434258874547192 
MAPE:	 4.511922179897357

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 44.2948843329178 
RMSE:	 6.655440205795392 
MAPE:	 5.1903345685841265

WMA
Prediction vs Close:		56.72% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 34.81241095672678 
RMSE:	 5.900204314829002 
MAPE:	 4.770935413189914

DEMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 52.107642174945944 
RMSE:	 7.2185623343534235 
MAPE:	 5.72607728989529
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.33 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4190.464, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3724.371, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.20 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3494.154, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3357.435, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.84 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.50 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3359.435, Time=0.16 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.233 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1674.717
Date:                Sun, 12 Dec 2021   AIC                           3357.435
Time:                        13:10:28   BIC                           3376.198
Sample:                             0   HQIC                          3364.641
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1955      0.003   -381.246      0.000      -1.202      -1.189
ar.L2         -0.8964      0.007   -135.835      0.000      -0.909      -0.883
ar.L3         -0.3971      0.006    -67.229      0.000      -0.409      -0.385
sigma2         3.7466      0.018    211.623      0.000       3.712       3.781
===================================================================================
Ljung-Box (L1) (Q):                  14.20   Jarque-Bera (JB):           2338363.32
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             3.76
Prob(H) (two-sided):                  0.00   Kurtosis:                       266.93
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_4 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_4 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.23368, saving model to LSTM1.h5
45/45 - 2s - loss: 0.2105 - val_loss: 0.2337 - lr: 0.0010 - 2s/epoch - 52ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.23368
45/45 - 0s - loss: 0.1425 - val_loss: 0.7288 - lr: 0.0010 - 495ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.23368
45/45 - 1s - loss: 0.1108 - val_loss: 0.9172 - lr: 0.0010 - 532ms/epoch - 12ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.23368 to 0.01871, saving model to LSTM1.h5
45/45 - 1s - loss: 0.0518 - val_loss: 0.0187 - lr: 0.0010 - 537ms/epoch - 12ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01871
45/45 - 0s - loss: 0.0458 - val_loss: 0.0336 - lr: 0.0010 - 482ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.01871
45/45 - 1s - loss: 0.0412 - val_loss: 0.0357 - lr: 0.0010 - 540ms/epoch - 12ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.01871 to 0.01275, saving model to LSTM1.h5
45/45 - 1s - loss: 0.0406 - val_loss: 0.0127 - lr: 0.0010 - 528ms/epoch - 12ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01275
45/45 - 1s - loss: 0.0437 - val_loss: 0.1432 - lr: 0.0010 - 533ms/epoch - 12ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.01275 to 0.00765, saving model to LSTM1.h5
45/45 - 1s - loss: 0.0366 - val_loss: 0.0076 - lr: 0.0010 - 524ms/epoch - 12ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0295 - val_loss: 0.0165 - lr: 0.0010 - 507ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0316 - val_loss: 0.0088 - lr: 0.0010 - 493ms/epoch - 11ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0327 - val_loss: 0.0238 - lr: 0.0010 - 493ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0304 - val_loss: 0.0176 - lr: 0.0010 - 513ms/epoch - 11ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00014: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0291 - val_loss: 0.0257 - lr: 0.0010 - 512ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0315 - val_loss: 0.0187 - lr: 1.0000e-04 - 488ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0276 - val_loss: 0.0148 - lr: 1.0000e-04 - 477ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0244 - val_loss: 0.0117 - lr: 1.0000e-04 - 516ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0244 - val_loss: 0.0117 - lr: 1.0000e-04 - 511ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00019: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0254 - val_loss: 0.0114 - lr: 1.0000e-04 - 499ms/epoch - 11ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0283 - val_loss: 0.0114 - lr: 1.0000e-05 - 476ms/epoch - 11ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0285 - val_loss: 0.0113 - lr: 1.0000e-05 - 501ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0254 - val_loss: 0.0114 - lr: 1.0000e-05 - 497ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0254 - val_loss: 0.0114 - lr: 1.0000e-05 - 479ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00024: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0297 - val_loss: 0.0114 - lr: 1.0000e-05 - 498ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0277 - val_loss: 0.0114 - lr: 1.0000e-05 - 463ms/epoch - 10ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0241 - val_loss: 0.0114 - lr: 1.0000e-05 - 490ms/epoch - 11ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0252 - val_loss: 0.0114 - lr: 1.0000e-05 - 507ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0257 - val_loss: 0.0114 - lr: 1.0000e-05 - 492ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0243 - val_loss: 0.0114 - lr: 1.0000e-05 - 477ms/epoch - 11ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0237 - val_loss: 0.0114 - lr: 1.0000e-05 - 488ms/epoch - 11ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0256 - val_loss: 0.0115 - lr: 1.0000e-05 - 479ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0263 - val_loss: 0.0115 - lr: 1.0000e-05 - 495ms/epoch - 11ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0255 - val_loss: 0.0114 - lr: 1.0000e-05 - 504ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0235 - val_loss: 0.0115 - lr: 1.0000e-05 - 507ms/epoch - 11ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0259 - val_loss: 0.0115 - lr: 1.0000e-05 - 501ms/epoch - 11ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0245 - val_loss: 0.0115 - lr: 1.0000e-05 - 486ms/epoch - 11ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0236 - val_loss: 0.0115 - lr: 1.0000e-05 - 513ms/epoch - 11ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0250 - val_loss: 0.0115 - lr: 1.0000e-05 - 526ms/epoch - 12ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0230 - val_loss: 0.0116 - lr: 1.0000e-05 - 500ms/epoch - 11ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0240 - val_loss: 0.0115 - lr: 1.0000e-05 - 528ms/epoch - 12ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0276 - val_loss: 0.0115 - lr: 1.0000e-05 - 492ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0244 - val_loss: 0.0116 - lr: 1.0000e-05 - 491ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0241 - val_loss: 0.0116 - lr: 1.0000e-05 - 489ms/epoch - 11ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0244 - val_loss: 0.0117 - lr: 1.0000e-05 - 481ms/epoch - 11ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0232 - val_loss: 0.0117 - lr: 1.0000e-05 - 498ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0240 - val_loss: 0.0119 - lr: 1.0000e-05 - 525ms/epoch - 12ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0255 - val_loss: 0.0120 - lr: 1.0000e-05 - 496ms/epoch - 11ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0273 - val_loss: 0.0122 - lr: 1.0000e-05 - 480ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0229 - val_loss: 0.0122 - lr: 1.0000e-05 - 497ms/epoch - 11ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0247 - val_loss: 0.0123 - lr: 1.0000e-05 - 480ms/epoch - 11ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0265 - val_loss: 0.0123 - lr: 1.0000e-05 - 508ms/epoch - 11ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0224 - val_loss: 0.0124 - lr: 1.0000e-05 - 492ms/epoch - 11ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0241 - val_loss: 0.0125 - lr: 1.0000e-05 - 486ms/epoch - 11ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0261 - val_loss: 0.0124 - lr: 1.0000e-05 - 494ms/epoch - 11ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0236 - val_loss: 0.0124 - lr: 1.0000e-05 - 482ms/epoch - 11ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0243 - val_loss: 0.0123 - lr: 1.0000e-05 - 478ms/epoch - 11ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0237 - val_loss: 0.0125 - lr: 1.0000e-05 - 497ms/epoch - 11ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00765
45/45 - 1s - loss: 0.0265 - val_loss: 0.0125 - lr: 1.0000e-05 - 514ms/epoch - 11ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00765
45/45 - 0s - loss: 0.0256 - val_loss: 0.0124 - lr: 1.0000e-05 - 489ms/epoch - 11ms/step
Epoch 00059: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 29.531169515594907 
RMSE:	 5.434258874547192 
MAPE:	 4.511922179897357

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 44.2948843329178 
RMSE:	 6.655440205795392 
MAPE:	 5.1903345685841265

WMA
Prediction vs Close:		56.72% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 34.81241095672678 
RMSE:	 5.900204314829002 
MAPE:	 4.770935413189914

DEMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 52.107642174945944 
RMSE:	 7.2185623343534235 
MAPE:	 5.72607728989529

KAMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 101.2314633840329 
RMSE:	 10.06138476473457 
MAPE:	 7.671150891933135
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.34 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4212.289, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3747.746, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.17 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3523.401, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3387.759, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.87 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.63 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3389.758, Time=0.16 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.373 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1689.879
Date:                Sun, 12 Dec 2021   AIC                           3387.759
Time:                        13:12:09   BIC                           3406.522
Sample:                             0   HQIC                          3394.964
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1878      0.003   -345.315      0.000      -1.195      -1.181
ar.L2         -0.8876      0.007   -121.809      0.000      -0.902      -0.873
ar.L3         -0.3957      0.007    -60.127      0.000      -0.409      -0.383
sigma2         3.8904      0.020    193.404      0.000       3.851       3.930
===================================================================================
Ljung-Box (L1) (Q):                  13.21   Jarque-Bera (JB):           1659080.01
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.08   Skew:                             3.28
Prob(H) (two-sided):                  0.00   Kurtosis:                       225.31
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_5 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_5 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04090, saving model to LSTM1.h5
58/58 - 2s - loss: 0.1551 - val_loss: 0.0409 - lr: 0.0010 - 2s/epoch - 42ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.04090 to 0.03024, saving model to LSTM1.h5
58/58 - 1s - loss: 0.0955 - val_loss: 0.0302 - lr: 0.0010 - 665ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.03024
58/58 - 1s - loss: 0.0563 - val_loss: 0.0304 - lr: 0.0010 - 619ms/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.03024
58/58 - 1s - loss: 0.0576 - val_loss: 0.1880 - lr: 0.0010 - 631ms/epoch - 11ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.03024 to 0.02879, saving model to LSTM1.h5
58/58 - 1s - loss: 0.0549 - val_loss: 0.0288 - lr: 0.0010 - 643ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.02879
58/58 - 1s - loss: 0.0463 - val_loss: 0.2561 - lr: 0.0010 - 606ms/epoch - 10ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.02879
58/58 - 1s - loss: 0.0456 - val_loss: 0.0770 - lr: 0.0010 - 630ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.02879
58/58 - 1s - loss: 0.0425 - val_loss: 0.0359 - lr: 0.0010 - 628ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.02879
58/58 - 1s - loss: 0.0396 - val_loss: 0.1726 - lr: 0.0010 - 614ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.02879 to 0.02841, saving model to LSTM1.h5
58/58 - 1s - loss: 0.0326 - val_loss: 0.0284 - lr: 0.0010 - 665ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.02841 to 0.01350, saving model to LSTM1.h5
58/58 - 1s - loss: 0.0343 - val_loss: 0.0135 - lr: 0.0010 - 631ms/epoch - 11ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0327 - val_loss: 0.0422 - lr: 0.0010 - 612ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0285 - val_loss: 0.0358 - lr: 0.0010 - 629ms/epoch - 11ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0289 - val_loss: 0.0340 - lr: 0.0010 - 629ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0253 - val_loss: 0.0301 - lr: 0.0010 - 632ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00016: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0283 - val_loss: 0.0324 - lr: 0.0010 - 616ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0280 - val_loss: 0.0233 - lr: 1.0000e-04 - 628ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0223 - val_loss: 0.0194 - lr: 1.0000e-04 - 608ms/epoch - 10ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0239 - val_loss: 0.0183 - lr: 1.0000e-04 - 641ms/epoch - 11ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0258 - val_loss: 0.0195 - lr: 1.0000e-04 - 615ms/epoch - 11ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00021: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0207 - val_loss: 0.0214 - lr: 1.0000e-04 - 610ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0210 - val_loss: 0.0216 - lr: 1.0000e-05 - 618ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0221 - val_loss: 0.0219 - lr: 1.0000e-05 - 635ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0236 - val_loss: 0.0222 - lr: 1.0000e-05 - 635ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0214 - val_loss: 0.0225 - lr: 1.0000e-05 - 624ms/epoch - 11ms/step
Epoch 26/500

Epoch 00026: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00026: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0222 - val_loss: 0.0226 - lr: 1.0000e-05 - 648ms/epoch - 11ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0196 - val_loss: 0.0226 - lr: 1.0000e-05 - 623ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0203 - val_loss: 0.0225 - lr: 1.0000e-05 - 617ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0207 - val_loss: 0.0226 - lr: 1.0000e-05 - 652ms/epoch - 11ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0222 - val_loss: 0.0228 - lr: 1.0000e-05 - 608ms/epoch - 10ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0210 - val_loss: 0.0234 - lr: 1.0000e-05 - 643ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0208 - val_loss: 0.0235 - lr: 1.0000e-05 - 605ms/epoch - 10ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0195 - val_loss: 0.0236 - lr: 1.0000e-05 - 611ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0212 - val_loss: 0.0236 - lr: 1.0000e-05 - 570ms/epoch - 10ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0209 - val_loss: 0.0239 - lr: 1.0000e-05 - 639ms/epoch - 11ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0236 - val_loss: 0.0240 - lr: 1.0000e-05 - 625ms/epoch - 11ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0217 - val_loss: 0.0237 - lr: 1.0000e-05 - 630ms/epoch - 11ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0227 - val_loss: 0.0233 - lr: 1.0000e-05 - 639ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0216 - val_loss: 0.0231 - lr: 1.0000e-05 - 631ms/epoch - 11ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0224 - val_loss: 0.0233 - lr: 1.0000e-05 - 612ms/epoch - 11ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0217 - val_loss: 0.0237 - lr: 1.0000e-05 - 657ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0192 - val_loss: 0.0244 - lr: 1.0000e-05 - 634ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0214 - val_loss: 0.0247 - lr: 1.0000e-05 - 608ms/epoch - 10ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0195 - val_loss: 0.0249 - lr: 1.0000e-05 - 643ms/epoch - 11ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0225 - val_loss: 0.0251 - lr: 1.0000e-05 - 645ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0196 - val_loss: 0.0252 - lr: 1.0000e-05 - 607ms/epoch - 10ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0204 - val_loss: 0.0251 - lr: 1.0000e-05 - 631ms/epoch - 11ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0201 - val_loss: 0.0253 - lr: 1.0000e-05 - 623ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0191 - val_loss: 0.0251 - lr: 1.0000e-05 - 638ms/epoch - 11ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0204 - val_loss: 0.0252 - lr: 1.0000e-05 - 626ms/epoch - 11ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0205 - val_loss: 0.0251 - lr: 1.0000e-05 - 600ms/epoch - 10ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0221 - val_loss: 0.0244 - lr: 1.0000e-05 - 646ms/epoch - 11ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0216 - val_loss: 0.0241 - lr: 1.0000e-05 - 638ms/epoch - 11ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0211 - val_loss: 0.0240 - lr: 1.0000e-05 - 609ms/epoch - 10ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0205 - val_loss: 0.0245 - lr: 1.0000e-05 - 617ms/epoch - 11ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0194 - val_loss: 0.0243 - lr: 1.0000e-05 - 650ms/epoch - 11ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0197 - val_loss: 0.0237 - lr: 1.0000e-05 - 642ms/epoch - 11ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0213 - val_loss: 0.0237 - lr: 1.0000e-05 - 625ms/epoch - 11ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0203 - val_loss: 0.0245 - lr: 1.0000e-05 - 598ms/epoch - 10ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0214 - val_loss: 0.0241 - lr: 1.0000e-05 - 635ms/epoch - 11ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.01350
58/58 - 1s - loss: 0.0209 - val_loss: 0.0246 - lr: 1.0000e-05 - 590ms/epoch - 10ms/step
Epoch 00061: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 29.531169515594907 
RMSE:	 5.434258874547192 
MAPE:	 4.511922179897357

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 44.2948843329178 
RMSE:	 6.655440205795392 
MAPE:	 5.1903345685841265

WMA
Prediction vs Close:		56.72% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 34.81241095672678 
RMSE:	 5.900204314829002 
MAPE:	 4.770935413189914

DEMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 52.107642174945944 
RMSE:	 7.2185623343534235 
MAPE:	 5.72607728989529

KAMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 101.2314633840329 
RMSE:	 10.06138476473457 
MAPE:	 7.671150891933135

MIDPOINT
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	45.15% Accuracy
MSE:	 120.91184599154492 
RMSE:	 10.995992269529154 
MAPE:	 9.137686493675425
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.35 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4414.515, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3944.062, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.28 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3715.173, Time=0.04 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3577.471, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.74 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.47 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3579.471, Time=0.17 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.211 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1784.736
Date:                Sun, 12 Dec 2021   AIC                           3577.471
Time:                        13:14:10   BIC                           3596.235
Sample:                             0   HQIC                          3584.677
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.844      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.861      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.862      0.000      -0.410      -0.387
sigma2         4.9242      0.023    215.469      0.000       4.879       4.969
===================================================================================
Ljung-Box (L1) (Q):                  14.55   Jarque-Bera (JB):           2468024.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       274.15
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_6 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_6 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.01665, saving model to LSTM1.h5
43/43 - 3s - loss: 0.3626 - val_loss: 0.0167 - lr: 0.0010 - 3s/epoch - 61ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.1414 - val_loss: 0.7987 - lr: 0.0010 - 452ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0695 - val_loss: 0.4506 - lr: 0.0010 - 461ms/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01665
43/43 - 1s - loss: 0.0630 - val_loss: 0.3210 - lr: 0.0010 - 503ms/epoch - 12ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0495 - val_loss: 0.1193 - lr: 0.0010 - 491ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0459 - val_loss: 0.1564 - lr: 0.0010 - 497ms/epoch - 12ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0563 - val_loss: 0.1495 - lr: 1.0000e-04 - 469ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0389 - val_loss: 0.1381 - lr: 1.0000e-04 - 488ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0338 - val_loss: 0.1357 - lr: 1.0000e-04 - 488ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0364 - val_loss: 0.1354 - lr: 1.0000e-04 - 470ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0355 - val_loss: 0.1289 - lr: 1.0000e-04 - 440ms/epoch - 10ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0373 - val_loss: 0.1286 - lr: 1.0000e-05 - 487ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0350 - val_loss: 0.1285 - lr: 1.0000e-05 - 478ms/epoch - 11ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0376 - val_loss: 0.1275 - lr: 1.0000e-05 - 486ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0348 - val_loss: 0.1263 - lr: 1.0000e-05 - 479ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0342 - val_loss: 0.1259 - lr: 1.0000e-05 - 481ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0372 - val_loss: 0.1257 - lr: 1.0000e-05 - 480ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0354 - val_loss: 0.1256 - lr: 1.0000e-05 - 463ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0331 - val_loss: 0.1254 - lr: 1.0000e-05 - 457ms/epoch - 11ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0353 - val_loss: 0.1266 - lr: 1.0000e-05 - 471ms/epoch - 11ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0351 - val_loss: 0.1278 - lr: 1.0000e-05 - 472ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0363 - val_loss: 0.1266 - lr: 1.0000e-05 - 463ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0340 - val_loss: 0.1259 - lr: 1.0000e-05 - 486ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0319 - val_loss: 0.1255 - lr: 1.0000e-05 - 468ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0361 - val_loss: 0.1252 - lr: 1.0000e-05 - 471ms/epoch - 11ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0352 - val_loss: 0.1254 - lr: 1.0000e-05 - 462ms/epoch - 11ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0349 - val_loss: 0.1266 - lr: 1.0000e-05 - 470ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0397 - val_loss: 0.1264 - lr: 1.0000e-05 - 487ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0318 - val_loss: 0.1269 - lr: 1.0000e-05 - 488ms/epoch - 11ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0344 - val_loss: 0.1264 - lr: 1.0000e-05 - 471ms/epoch - 11ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0310 - val_loss: 0.1264 - lr: 1.0000e-05 - 478ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0332 - val_loss: 0.1250 - lr: 1.0000e-05 - 475ms/epoch - 11ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0356 - val_loss: 0.1249 - lr: 1.0000e-05 - 453ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0347 - val_loss: 0.1252 - lr: 1.0000e-05 - 499ms/epoch - 12ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0345 - val_loss: 0.1239 - lr: 1.0000e-05 - 475ms/epoch - 11ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01665
43/43 - 1s - loss: 0.0343 - val_loss: 0.1241 - lr: 1.0000e-05 - 520ms/epoch - 12ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0370 - val_loss: 0.1235 - lr: 1.0000e-05 - 445ms/epoch - 10ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0391 - val_loss: 0.1238 - lr: 1.0000e-05 - 468ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0361 - val_loss: 0.1240 - lr: 1.0000e-05 - 449ms/epoch - 10ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0383 - val_loss: 0.1246 - lr: 1.0000e-05 - 463ms/epoch - 11ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0342 - val_loss: 0.1245 - lr: 1.0000e-05 - 485ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0379 - val_loss: 0.1233 - lr: 1.0000e-05 - 465ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0311 - val_loss: 0.1220 - lr: 1.0000e-05 - 496ms/epoch - 12ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0370 - val_loss: 0.1218 - lr: 1.0000e-05 - 452ms/epoch - 11ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0359 - val_loss: 0.1224 - lr: 1.0000e-05 - 474ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0323 - val_loss: 0.1219 - lr: 1.0000e-05 - 455ms/epoch - 11ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0328 - val_loss: 0.1222 - lr: 1.0000e-05 - 479ms/epoch - 11ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0339 - val_loss: 0.1208 - lr: 1.0000e-05 - 468ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01665
43/43 - 1s - loss: 0.0327 - val_loss: 0.1212 - lr: 1.0000e-05 - 510ms/epoch - 12ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0354 - val_loss: 0.1205 - lr: 1.0000e-05 - 471ms/epoch - 11ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01665
43/43 - 0s - loss: 0.0366 - val_loss: 0.1210 - lr: 1.0000e-05 - 489ms/epoch - 11ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 29.531169515594907 
RMSE:	 5.434258874547192 
MAPE:	 4.511922179897357

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 44.2948843329178 
RMSE:	 6.655440205795392 
MAPE:	 5.1903345685841265

WMA
Prediction vs Close:		56.72% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 34.81241095672678 
RMSE:	 5.900204314829002 
MAPE:	 4.770935413189914

DEMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 52.107642174945944 
RMSE:	 7.2185623343534235 
MAPE:	 5.72607728989529

KAMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 101.2314633840329 
RMSE:	 10.06138476473457 
MAPE:	 7.671150891933135

MIDPOINT
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	45.15% Accuracy
MSE:	 120.91184599154492 
RMSE:	 10.995992269529154 
MAPE:	 9.137686493675425

T3
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 41.51394815576297 
RMSE:	 6.443131859256255 
MAPE:	 5.507945991108928
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.42 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4352.703, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3889.412, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.18 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3689.930, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3574.245, Time=0.06 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.84 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.57 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3576.245, Time=0.14 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.315 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1783.123
Date:                Sun, 12 Dec 2021   AIC                           3574.245
Time:                        13:15:36   BIC                           3593.008
Sample:                             0   HQIC                          3581.451
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1480      0.004   -302.430      0.000      -1.155      -1.141
ar.L2         -0.8300      0.008    -99.682      0.000      -0.846      -0.814
ar.L3         -0.3687      0.007    -50.527      0.000      -0.383      -0.354
sigma2         4.9055      0.028    175.970      0.000       4.851       4.960
===================================================================================
Ljung-Box (L1) (Q):                  11.61   Jarque-Bera (JB):           1261976.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.16   Skew:                             2.52
Prob(H) (two-sided):                  0.00   Kurtosis:                       196.90
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_7 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_7 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.25314, saving model to LSTM1.h5
90/90 - 3s - loss: 0.1518 - val_loss: 0.2531 - lr: 0.0010 - 3s/epoch - 31ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.25314
90/90 - 1s - loss: 0.1497 - val_loss: 0.3602 - lr: 0.0010 - 967ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.25314
90/90 - 1s - loss: 0.0931 - val_loss: 0.6540 - lr: 0.0010 - 1s/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.25314 to 0.05296, saving model to LSTM1.h5
90/90 - 1s - loss: 0.0483 - val_loss: 0.0530 - lr: 0.0010 - 1s/epoch - 11ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.05296 to 0.01559, saving model to LSTM1.h5
90/90 - 1s - loss: 0.0433 - val_loss: 0.0156 - lr: 0.0010 - 1s/epoch - 11ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0839 - val_loss: 0.2820 - lr: 0.0010 - 1s/epoch - 11ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0469 - val_loss: 0.0236 - lr: 0.0010 - 993ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0354 - val_loss: 0.0255 - lr: 0.0010 - 968ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0317 - val_loss: 0.1175 - lr: 0.0010 - 930ms/epoch - 10ms/step
Epoch 10/500

Epoch 00010: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00010: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0339 - val_loss: 0.0198 - lr: 0.0010 - 964ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0410 - val_loss: 0.0293 - lr: 1.0000e-04 - 1s/epoch - 11ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0274 - val_loss: 0.0284 - lr: 1.0000e-04 - 982ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0260 - val_loss: 0.0286 - lr: 1.0000e-04 - 997ms/epoch - 11ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0252 - val_loss: 0.0239 - lr: 1.0000e-04 - 944ms/epoch - 10ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00015: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0254 - val_loss: 0.0185 - lr: 1.0000e-04 - 943ms/epoch - 10ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0253 - val_loss: 0.0190 - lr: 1.0000e-05 - 953ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0252 - val_loss: 0.0192 - lr: 1.0000e-05 - 929ms/epoch - 10ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0240 - val_loss: 0.0195 - lr: 1.0000e-05 - 963ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0229 - val_loss: 0.0204 - lr: 1.0000e-05 - 860ms/epoch - 10ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00020: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0231 - val_loss: 0.0212 - lr: 1.0000e-05 - 977ms/epoch - 11ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0239 - val_loss: 0.0210 - lr: 1.0000e-05 - 955ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0235 - val_loss: 0.0209 - lr: 1.0000e-05 - 921ms/epoch - 10ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0242 - val_loss: 0.0212 - lr: 1.0000e-05 - 938ms/epoch - 10ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0221 - val_loss: 0.0208 - lr: 1.0000e-05 - 942ms/epoch - 10ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0219 - val_loss: 0.0201 - lr: 1.0000e-05 - 970ms/epoch - 11ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0234 - val_loss: 0.0200 - lr: 1.0000e-05 - 1s/epoch - 11ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0228 - val_loss: 0.0202 - lr: 1.0000e-05 - 963ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0242 - val_loss: 0.0200 - lr: 1.0000e-05 - 939ms/epoch - 10ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0244 - val_loss: 0.0196 - lr: 1.0000e-05 - 949ms/epoch - 11ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0253 - val_loss: 0.0199 - lr: 1.0000e-05 - 942ms/epoch - 10ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0226 - val_loss: 0.0213 - lr: 1.0000e-05 - 970ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0231 - val_loss: 0.0222 - lr: 1.0000e-05 - 977ms/epoch - 11ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0245 - val_loss: 0.0231 - lr: 1.0000e-05 - 992ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0216 - val_loss: 0.0234 - lr: 1.0000e-05 - 959ms/epoch - 11ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0226 - val_loss: 0.0237 - lr: 1.0000e-05 - 985ms/epoch - 11ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0241 - val_loss: 0.0238 - lr: 1.0000e-05 - 983ms/epoch - 11ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0232 - val_loss: 0.0237 - lr: 1.0000e-05 - 998ms/epoch - 11ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0250 - val_loss: 0.0240 - lr: 1.0000e-05 - 988ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0243 - val_loss: 0.0240 - lr: 1.0000e-05 - 941ms/epoch - 10ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0229 - val_loss: 0.0242 - lr: 1.0000e-05 - 978ms/epoch - 11ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0210 - val_loss: 0.0239 - lr: 1.0000e-05 - 952ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0214 - val_loss: 0.0232 - lr: 1.0000e-05 - 955ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0238 - val_loss: 0.0230 - lr: 1.0000e-05 - 941ms/epoch - 10ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0223 - val_loss: 0.0218 - lr: 1.0000e-05 - 916ms/epoch - 10ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0214 - val_loss: 0.0215 - lr: 1.0000e-05 - 951ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0213 - val_loss: 0.0216 - lr: 1.0000e-05 - 972ms/epoch - 11ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0231 - val_loss: 0.0227 - lr: 1.0000e-05 - 977ms/epoch - 11ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0214 - val_loss: 0.0241 - lr: 1.0000e-05 - 962ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0226 - val_loss: 0.0243 - lr: 1.0000e-05 - 905ms/epoch - 10ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0221 - val_loss: 0.0238 - lr: 1.0000e-05 - 982ms/epoch - 11ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0212 - val_loss: 0.0232 - lr: 1.0000e-05 - 1s/epoch - 11ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0214 - val_loss: 0.0243 - lr: 1.0000e-05 - 981ms/epoch - 11ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0213 - val_loss: 0.0233 - lr: 1.0000e-05 - 941ms/epoch - 10ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0224 - val_loss: 0.0222 - lr: 1.0000e-05 - 983ms/epoch - 11ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01559
90/90 - 1s - loss: 0.0227 - val_loss: 0.0225 - lr: 1.0000e-05 - 989ms/epoch - 11ms/step
Epoch 00055: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 29.531169515594907 
RMSE:	 5.434258874547192 
MAPE:	 4.511922179897357

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 44.2948843329178 
RMSE:	 6.655440205795392 
MAPE:	 5.1903345685841265

WMA
Prediction vs Close:		56.72% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 34.81241095672678 
RMSE:	 5.900204314829002 
MAPE:	 4.770935413189914

DEMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 52.107642174945944 
RMSE:	 7.2185623343534235 
MAPE:	 5.72607728989529

KAMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 101.2314633840329 
RMSE:	 10.06138476473457 
MAPE:	 7.671150891933135

MIDPOINT
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	45.15% Accuracy
MSE:	 120.91184599154492 
RMSE:	 10.995992269529154 
MAPE:	 9.137686493675425

T3
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 41.51394815576297 
RMSE:	 6.443131859256255 
MAPE:	 5.507945991108928

TEMA
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 72.3302204365722 
RMSE:	 8.504717540081634 
MAPE:	 7.413730210152267
Runtime: mins: 13.87277515

Architecture used

In [ ]:
from google.colab import files
import cv2
uploaded = files.upload()
Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to enable. 
Saving Experiment1.png to Experiment1 (2).png
In [ ]:
img = cv2.imread('Experiment1.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)
Out[ ]:
<matplotlib.image.AxesImage at 0x7fb48e943550>

Excess kurtosis is a metric that compares the kurtosis of a distribution against the kurtosis of a normal distribution. The kurtosis of a normal distribution equals 3. Therefore, the excess kurtosis is found using the formula below:

Excess Kurtosis = Kurtosis – 3

Model Plots

In [ ]:
np.save("X_train_appl.npy", X_train)
np.save("y_train_appl.npy", y_train)
np.save("X_test_appl.npy", X_test)
np.save("y_test_appl.npy", y_test)
np.save("yc_train_appl.npy", yc_train)
np.save("yc_test_appl.npy", yc_test)
np.save('index_train_appl.npy', index_train)
np.save('index_test_appl.npy', index_test)
In [ ]:
list(simulation1.keys())
Out[ ]:
['SMA', 'EMA', 'WMA', 'DEMA', 'KAMA', 'MIDPOINT', 'T3', 'TEMA']
In [97]:
with open('simulation1_data.json') as json_file:
    simulation1 = json.load(json_file)
fileimg = 'Experiment1'
In [98]:
for i in range(len(list(simulation1.keys()))):
  SIM = list(simulation1.keys())[i]
  plot_train(simulation1,SIM)
  plot_test(simulation1,SIM)

----- Train RMSE for SMA ----- 7.935503486463878
----- Train_MSE_LSTM for SMA ----- 62.97221558368037
----- Train MAE LSTM for SMA ----- 6.979776083083713

----- Test RMSE for SMA----- 5.434258874547192
----- Test_MSE_LSTM for SMA----- 29.531169515594907
----- Test_MAE_LSTM for SMA----- 4.511922179897357

----- Train RMSE for EMA ----- 9.402372564274692
----- Train_MSE_LSTM for EMA ----- 88.40460983742544
----- Train MAE LSTM for EMA ----- 8.28586532352354

----- Test RMSE for EMA----- 6.655440205795392
----- Test_MSE_LSTM for EMA----- 44.2948843329178
----- Test_MAE_LSTM for EMA----- 5.1903345685841265

----- Train RMSE for WMA ----- 9.895902209840198
----- Train_MSE_LSTM for WMA ----- 97.92888054672011
----- Train MAE LSTM for WMA ----- 8.733617713903124

----- Test RMSE for WMA----- 5.900204314829002
----- Test_MSE_LSTM for WMA----- 34.81241095672678
----- Test_MAE_LSTM for WMA----- 4.770935413189914

----- Train RMSE for DEMA ----- 10.759004484921052
----- Train_MSE_LSTM for DEMA ----- 115.75617750655131
----- Train MAE LSTM for DEMA ----- 9.577381117820352

----- Test RMSE for DEMA----- 7.2185623343534235
----- Test_MSE_LSTM for DEMA----- 52.107642174945944
----- Test_MAE_LSTM for DEMA----- 5.72607728989529

----- Train RMSE for KAMA ----- 9.565138688518502
----- Train_MSE_LSTM for KAMA ----- 91.49187813059346
----- Train MAE LSTM for KAMA ----- 8.554695393558186

----- Test RMSE for KAMA----- 10.06138476473457
----- Test_MSE_LSTM for KAMA----- 101.2314633840329
----- Test_MAE_LSTM for KAMA----- 7.671150891933135

----- Train RMSE for MIDPOINT ----- 8.472630816745282
----- Train_MSE_LSTM for MIDPOINT ----- 71.78547295686181
----- Train MAE LSTM for MIDPOINT ----- 7.568616716744433

----- Test RMSE for MIDPOINT----- 10.995992269529154
----- Test_MSE_LSTM for MIDPOINT----- 120.91184599154492
----- Test_MAE_LSTM for MIDPOINT----- 9.137686493675425

----- Train RMSE for T3 ----- 10.697204443760125
----- Train_MSE_LSTM for T3 ----- 114.43018291160138
----- Train MAE LSTM for T3 ----- 9.607836069383296

----- Test RMSE for T3----- 6.443131859256255
----- Test_MSE_LSTM for T3----- 41.51394815576297
----- Test_MAE_LSTM for T3----- 5.507945991108928

----- Train RMSE for TEMA ----- 6.840259844014339
----- Train_MSE_LSTM for TEMA ----- 46.78915473363507
----- Train MAE LSTM for TEMA ----- 4.502232091756086

----- Test RMSE for TEMA----- 8.504717540081634
----- Test_MSE_LSTM for TEMA----- 72.3302204365722
----- Test_MAE_LSTM for TEMA----- 7.413730210152267

Univariate Arima Multistep MutiVariate LSTM Hybrid Model Experiment 2

In [ ]:
def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # # Option 1
    # # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # option 2
    model = Sequential()
    model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    model.add(Dense(64))
    model.add(Dense(units=output_dim))
    model.compile(optimizer=Adam(learning_rate = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM2.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()




    # Option 3
    # define custom activation
    # 
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te
In [ ]:
if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation2 = {}
    imgfile = 'Experiment2'
    for ma in optimized_period:
              print(ma)
              print(functions[ma])
              print ( int( optimized_period[ma]))
            # if ma == 'SMA':
              low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
              low_vol = low_vol.fillna(0)
              low_vol_data = df['close']
              high_vol = pd.DataFrame()
              df2 = df.copy()
              for i in df2.columns:
                if i in low_vol.columns:
                  high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
              high_vol_data = df['close']
              ## *****************************************************
              # Generate ARIMA and LSTM predictions
              print('\nWorking on ' + ma + ' predictions')
              try:
                print('parameters used : ', train_len, test_len)
                low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima(low_vol,low_vol_data, train_len, test_len)
              except:
                  print('ARIMA error, skipping to next MA type')
                  continue
              Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
              final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
              mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
              rmse_ftr = mse_ftr ** 0.5
              mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
              mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

              final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
              mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
              rmse = mse ** 0.5
              mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              # Generate prediction accuracy
              actual = df['close'].tail(test_len).values
              result_1 = []
              result_2 = []
              for i in range(1, len(final_prediction)):
                  # Compare prediction to previous close price
                  if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                      result_1.append(1)
                  elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                      result_1.append(1)
                  else:
                      result_1.append(0)

                  # Compare prediction to previous prediction
                  if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                      result_2.append(1)
                  elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                      result_2.append(1)
                  else:
                      result_2.append(0)

              accuracy_1 = np.mean(result_1)
              accuracy_2 = np.mean(result_2)

              simulation2[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                            'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                            'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                            'rmse': rmse_ftr, 'mae' : mae_ftr},
                                'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                          'rmse': rmse, 'mae': mae },
                                'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

              # save simulation data here as checkpoint
              with open('simulation2_data.json', 'w') as fp:
                  json.dump(simulation2, fp)

              for ma in simulation2.keys():
                  print('\n' + ma)
                  print('Prediction vs Close:\t\t' + str(round(100*simulation2[ma]['accuracy']['prediction vs close'], 2))
                        + '% Accuracy')
                  print('Prediction vs Prediction:\t' + str(round(100*simulation2[ma]['accuracy']['prediction vs prediction'], 2))
                        + '% Accuracy')
                  print('MSE:\t', simulation2[ma]['final']['mse'],
                        '\nRMSE:\t', simulation2[ma]['final']['rmse'],
                        '\nMAPE:\t', simulation2[ma]['final']['mae'])#,
                        # '\nMAPE:\t', simulation[ma]['final']['mape'])
            # else:
            #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.44 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4157.020, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3687.148, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.14 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3458.651, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3322.133, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.53 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.57 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3324.133, Time=0.15 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.049 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1657.067
Date:                Sun, 12 Dec 2021   AIC                           3322.133
Time:                        13:21:51   BIC                           3340.897
Sample:                             0   HQIC                          3329.339
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1966      0.003   -387.226      0.000      -1.203      -1.191
ar.L2         -0.8952      0.006   -138.692      0.000      -0.908      -0.883
ar.L3         -0.3968      0.006    -68.284      0.000      -0.408      -0.385
sigma2         3.5858      0.017    214.535      0.000       3.553       3.619
===================================================================================
Ljung-Box (L1) (Q):                  14.47   Jarque-Bera (JB):           2428881.42
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       271.99
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.15003, saving model to LSTM2.h5
48/48 - 6s - loss: 0.1416 - accuracy: 0.0000e+00 - val_loss: 0.1500 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 6s/epoch - 133ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.15003 to 0.00567, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0666 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 0.0010 - 359ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00567
48/48 - 0s - loss: 0.0245 - accuracy: 0.0000e+00 - val_loss: 0.1272 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 318ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00567
48/48 - 0s - loss: 0.0281 - accuracy: 0.0000e+00 - val_loss: 0.0126 - val_accuracy: 0.0037 - lr: 0.0010 - 313ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00567
48/48 - 0s - loss: 0.0131 - accuracy: 0.0000e+00 - val_loss: 0.1042 - val_accuracy: 0.0037 - lr: 0.0010 - 328ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.00567 to 0.00338, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0129 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 0.0010 - 327ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0044 - accuracy: 0.0000e+00 - val_loss: 0.0397 - val_accuracy: 0.0037 - lr: 0.0010 - 309ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0043 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 0.0010 - 313ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0234 - val_accuracy: 0.0037 - lr: 0.0010 - 311ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0124 - val_accuracy: 0.0037 - lr: 0.0010 - 328ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0195 - val_accuracy: 0.0037 - lr: 0.0010 - 322ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0038 - accuracy: 0.0000e+00 - val_loss: 0.0103 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 321ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0100 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 330ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 336ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 325ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0082 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 325ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 322ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 330ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 329ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 334ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 335ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 322ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 328ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 324ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 330ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 322ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 321ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 322ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 336ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 318ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 325ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 326ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 325ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 324ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 317ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 320ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 317ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 331ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 314ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 290ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 297ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 319ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 314ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 324ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 330ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 311ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 317ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 322ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 327ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 321ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 327ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 323ms/epoch - 7ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 321ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 322ms/epoch - 7ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00338
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 313ms/epoch - 7ms/step
Epoch 00056: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 63.041023819643854 
RMSE:	 7.939837770360541 
MAPE:	 6.449589599500938
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4231.556, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3761.238, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.20 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3532.227, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3394.496, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.04 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.51 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3396.496, Time=0.26 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.567 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1693.248
Date:                Sun, 12 Dec 2021   AIC                           3394.496
Time:                        13:23:19   BIC                           3413.260
Sample:                             0   HQIC                          3401.702
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.569      0.000      -1.204      -1.192
ar.L2         -0.8976      0.006   -139.811      0.000      -0.910      -0.885
ar.L3         -0.3984      0.006    -68.662      0.000      -0.410      -0.387
sigma2         3.9230      0.018    215.372      0.000       3.887       3.959
===================================================================================
Ljung-Box (L1) (Q):                  14.54   Jarque-Bera (JB):           2462173.05
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.82
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04754, saving model to LSTM2.h5
16/16 - 5s - loss: 0.0550 - accuracy: 0.0000e+00 - val_loss: 0.0475 - val_accuracy: 0.0037 - lr: 0.0010 - 5s/epoch - 295ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.04754 to 0.04458, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0050 - accuracy: 0.0000e+00 - val_loss: 0.0446 - val_accuracy: 0.0037 - lr: 0.0010 - 158ms/epoch - 10ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.04458 to 0.01126, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0138 - accuracy: 0.0000e+00 - val_loss: 0.0113 - val_accuracy: 0.0037 - lr: 0.0010 - 159ms/epoch - 10ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01126
16/16 - 0s - loss: 0.0062 - accuracy: 0.0000e+00 - val_loss: 0.1306 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 135ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01126
16/16 - 0s - loss: 0.0341 - accuracy: 0.0000e+00 - val_loss: 0.0492 - val_accuracy: 0.0037 - lr: 0.0010 - 130ms/epoch - 8ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.01126
16/16 - 0s - loss: 0.0235 - accuracy: 0.0000e+00 - val_loss: 0.1911 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 136ms/epoch - 9ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01126
16/16 - 0s - loss: 0.0638 - accuracy: 0.0000e+00 - val_loss: 0.0348 - val_accuracy: 0.0037 - lr: 0.0010 - 126ms/epoch - 8ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.01126 to 0.00602, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0400 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 0.0010 - 154ms/epoch - 10ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00602
16/16 - 0s - loss: 0.0047 - accuracy: 0.0000e+00 - val_loss: 0.0114 - val_accuracy: 0.0037 - lr: 0.0010 - 121ms/epoch - 8ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00602
16/16 - 0s - loss: 0.0032 - accuracy: 0.0000e+00 - val_loss: 0.0068 - val_accuracy: 0.0037 - lr: 0.0010 - 126ms/epoch - 8ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.00602 to 0.00571, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 0.0010 - 160ms/epoch - 10ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.00571 to 0.00529, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 0.0010 - 157ms/epoch - 10ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00529
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 0.0010 - 135ms/epoch - 8ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.00529 to 0.00528, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 0.0010 - 159ms/epoch - 10ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00528
16/16 - 0s - loss: 9.0025e-04 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 0.0010 - 124ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.00528 to 0.00527, saving model to LSTM2.h5
16/16 - 0s - loss: 8.7937e-04 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 0.0010 - 152ms/epoch - 9ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00017: val_loss improved from 0.00527 to 0.00524, saving model to LSTM2.h5
16/16 - 0s - loss: 8.7268e-04 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 0.0010 - 157ms/epoch - 10ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.2758e-04 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 126ms/epoch - 8ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.2223e-04 - accuracy: 0.0000e+00 - val_loss: 0.0054 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 126ms/epoch - 8ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1901e-04 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 134ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1682e-04 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 126ms/epoch - 8ms/step
Epoch 22/500

Epoch 00022: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00022: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1479e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 130ms/epoch - 8ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1269e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 125ms/epoch - 8ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1248e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1227e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 126ms/epoch - 8ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1206e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 132ms/epoch - 8ms/step
Epoch 27/500

Epoch 00027: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00027: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1184e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1162e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1140e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1117e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 136ms/epoch - 9ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1094e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 126ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1071e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 136ms/epoch - 9ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1048e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 127ms/epoch - 8ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.1024e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 138ms/epoch - 9ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0999e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0975e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 136ms/epoch - 9ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0950e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 125ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0924e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 128ms/epoch - 8ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0899e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0873e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 134ms/epoch - 8ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0846e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 124ms/epoch - 8ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0820e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 126ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0793e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 127ms/epoch - 8ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0766e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 124ms/epoch - 8ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0738e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0710e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0682e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 134ms/epoch - 8ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0653e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0624e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0595e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 136ms/epoch - 9ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0566e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 132ms/epoch - 8ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0536e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0506e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 134ms/epoch - 8ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0475e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0444e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 123ms/epoch - 8ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0413e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 120ms/epoch - 8ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0382e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0350e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 135ms/epoch - 8ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0318e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0286e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 126ms/epoch - 8ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0253e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0220e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 128ms/epoch - 8ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0187e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0154e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0120e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 126ms/epoch - 8ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0086e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 136ms/epoch - 9ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.00524
16/16 - 0s - loss: 8.0051e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 00067: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 63.041023819643854 
RMSE:	 7.939837770360541 
MAPE:	 6.449589599500938

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 63.66877348603133 
RMSE:	 7.979271488427457 
MAPE:	 6.567170782771208
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4264.089, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3793.930, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.18 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3564.923, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3427.258, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.54 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.39 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3429.258, Time=0.23 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.925 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1709.629
Date:                Sun, 12 Dec 2021   AIC                           3427.258
Time:                        13:24:45   BIC                           3446.021
Sample:                             0   HQIC                          3434.464
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1981      0.003   -389.386      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.699      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.737      0.000      -0.410      -0.387
sigma2         4.0860      0.019    215.311      0.000       4.049       4.123
===================================================================================
Ljung-Box (L1) (Q):                  14.57   Jarque-Bera (JB):           2460901.70
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.75
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.12010, saving model to LSTM2.h5
17/17 - 5s - loss: 0.1148 - accuracy: 0.0000e+00 - val_loss: 0.1201 - val_accuracy: 0.0037 - lr: 0.0010 - 5s/epoch - 308ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.12010 to 0.06339, saving model to LSTM2.h5
17/17 - 0s - loss: 0.0413 - accuracy: 0.0000e+00 - val_loss: 0.0634 - val_accuracy: 0.0037 - lr: 0.0010 - 152ms/epoch - 9ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.06339 to 0.00588, saving model to LSTM2.h5
17/17 - 0s - loss: 0.0254 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 0.0010 - 152ms/epoch - 9ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00588
17/17 - 0s - loss: 0.0036 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 0.0010 - 133ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00588
17/17 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 0.0010 - 140ms/epoch - 8ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00588
17/17 - 0s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 0.0010 - 133ms/epoch - 8ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00588
17/17 - 0s - loss: 0.0032 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 0.0010 - 124ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00008: val_loss did not improve from 0.00588
17/17 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 0.0010 - 136ms/epoch - 8ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00588
17/17 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 133ms/epoch - 8ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.9539e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 129ms/epoch - 8ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.7712e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 132ms/epoch - 8ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.6213e-04 - accuracy: 0.0000e+00 - val_loss: 0.0082 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 136ms/epoch - 8ms/step
Epoch 13/500

Epoch 00013: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00013: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.6037e-04 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 132ms/epoch - 8ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.5004e-04 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 140ms/epoch - 8ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4966e-04 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 139ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4931e-04 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 126ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4897e-04 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 134ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00018: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4862e-04 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 140ms/epoch - 8ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4826e-04 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 144ms/epoch - 8ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4789e-04 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 141ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4750e-04 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 137ms/epoch - 8ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4711e-04 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4671e-04 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4629e-04 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 132ms/epoch - 8ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4587e-04 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 140ms/epoch - 8ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4544e-04 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 137ms/epoch - 8ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4500e-04 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 142ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4456e-04 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 136ms/epoch - 8ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4411e-04 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4365e-04 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4318e-04 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 132ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4270e-04 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 134ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4222e-04 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 141ms/epoch - 8ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4173e-04 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 132ms/epoch - 8ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4124e-04 - accuracy: 0.0000e+00 - val_loss: 0.0088 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 132ms/epoch - 8ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4073e-04 - accuracy: 0.0000e+00 - val_loss: 0.0088 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 144ms/epoch - 8ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.4022e-04 - accuracy: 0.0000e+00 - val_loss: 0.0088 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 137ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3971e-04 - accuracy: 0.0000e+00 - val_loss: 0.0088 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 137ms/epoch - 8ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3918e-04 - accuracy: 0.0000e+00 - val_loss: 0.0088 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 144ms/epoch - 8ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3865e-04 - accuracy: 0.0000e+00 - val_loss: 0.0089 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 135ms/epoch - 8ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3811e-04 - accuracy: 0.0000e+00 - val_loss: 0.0089 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 138ms/epoch - 8ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3757e-04 - accuracy: 0.0000e+00 - val_loss: 0.0089 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 142ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3701e-04 - accuracy: 0.0000e+00 - val_loss: 0.0089 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 135ms/epoch - 8ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3645e-04 - accuracy: 0.0000e+00 - val_loss: 0.0089 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 126ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3589e-04 - accuracy: 0.0000e+00 - val_loss: 0.0089 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3531e-04 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 125ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3473e-04 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3414e-04 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 128ms/epoch - 8ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3355e-04 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 134ms/epoch - 8ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3295e-04 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 140ms/epoch - 8ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3234e-04 - accuracy: 0.0000e+00 - val_loss: 0.0091 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 127ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3172e-04 - accuracy: 0.0000e+00 - val_loss: 0.0091 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00588
17/17 - 0s - loss: 9.3110e-04 - accuracy: 0.0000e+00 - val_loss: 0.0091 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 126ms/epoch - 7ms/step
Epoch 00053: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 63.041023819643854 
RMSE:	 7.939837770360541 
MAPE:	 6.449589599500938

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 63.66877348603133 
RMSE:	 7.979271488427457 
MAPE:	 6.567170782771208

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 74.84193590201411 
RMSE:	 8.65112338959595 
MAPE:	 6.92726320779593
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4436.126, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3965.317, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.28 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3736.589, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3598.951, Time=0.06 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.10 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.73 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3600.951, Time=0.24 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.897 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1795.475
Date:                Sun, 12 Dec 2021   AIC                           3598.951
Time:                        13:26:17   BIC                           3617.714
Sample:                             0   HQIC                          3606.157
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1983      0.003   -389.581      0.000      -1.204      -1.192
ar.L2         -0.8973      0.006   -139.732      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.649      0.000      -0.410      -0.387
sigma2         5.0573      0.023    215.292      0.000       5.011       5.103
===================================================================================
Ljung-Box (L1) (Q):                  14.41   Jarque-Bera (JB):           2460553.80
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.89
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.06980, saving model to LSTM2.h5
10/10 - 5s - loss: 0.2671 - accuracy: 0.0000e+00 - val_loss: 0.0698 - val_accuracy: 0.0037 - lr: 0.0010 - 5s/epoch - 512ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.06980 to 0.01999, saving model to LSTM2.h5
10/10 - 0s - loss: 0.0727 - accuracy: 0.0000e+00 - val_loss: 0.0200 - val_accuracy: 0.0037 - lr: 0.0010 - 126ms/epoch - 13ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01999
10/10 - 0s - loss: 0.0179 - accuracy: 0.0000e+00 - val_loss: 0.0490 - val_accuracy: 0.0037 - lr: 0.0010 - 98ms/epoch - 10ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01999
10/10 - 0s - loss: 0.0061 - accuracy: 0.0000e+00 - val_loss: 0.0307 - val_accuracy: 0.0037 - lr: 0.0010 - 97ms/epoch - 10ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01999
10/10 - 0s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0213 - val_accuracy: 0.0037 - lr: 0.0010 - 94ms/epoch - 9ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.01999 to 0.01766, saving model to LSTM2.h5
10/10 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0177 - val_accuracy: 0.0037 - lr: 0.0010 - 118ms/epoch - 12ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0220 - val_accuracy: 0.0037 - lr: 0.0010 - 90ms/epoch - 9ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0247 - val_accuracy: 0.0037 - lr: 0.0010 - 90ms/epoch - 9ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0249 - val_accuracy: 0.0037 - lr: 0.0010 - 89ms/epoch - 9ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0239 - val_accuracy: 0.0037 - lr: 0.0010 - 95ms/epoch - 10ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0252 - val_accuracy: 0.0037 - lr: 0.0010 - 91ms/epoch - 9ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0253 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 94ms/epoch - 9ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0255 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 98ms/epoch - 10ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0256 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 96ms/epoch - 10ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0258 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 88ms/epoch - 9ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0259 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 91ms/epoch - 9ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0259 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 95ms/epoch - 10ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0260 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0260 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0260 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 10ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0260 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 9ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0260 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 98ms/epoch - 10ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0260 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 10ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0261 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 10ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0261 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0261 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0261 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0261 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0261 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 10ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0262 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0262 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0262 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 85ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0262 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 10ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0262 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 10ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0262 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 10ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0263 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0263 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 95ms/epoch - 10ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0263 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 84ms/epoch - 8ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0263 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0263 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 85ms/epoch - 8ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0263 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0264 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0264 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0264 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 10ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0264 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 99ms/epoch - 10ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0264 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0265 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0265 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 95ms/epoch - 9ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0265 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0265 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0265 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 85ms/epoch - 9ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0265 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0266 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0266 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0266 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 99ms/epoch - 10ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01766
10/10 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0266 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 00056: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 63.041023819643854 
RMSE:	 7.939837770360541 
MAPE:	 6.449589599500938

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 63.66877348603133 
RMSE:	 7.979271488427457 
MAPE:	 6.567170782771208

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 74.84193590201411 
RMSE:	 8.65112338959595 
MAPE:	 6.92726320779593

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 124.07774757087437 
RMSE:	 11.139019147612341 
MAPE:	 9.962964959911572
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.32 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4190.464, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3724.371, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.21 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3494.154, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3357.435, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.35 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.57 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3359.435, Time=0.26 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.913 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1674.717
Date:                Sun, 12 Dec 2021   AIC                           3357.435
Time:                        13:27:32   BIC                           3376.198
Sample:                             0   HQIC                          3364.641
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1955      0.003   -381.246      0.000      -1.202      -1.189
ar.L2         -0.8964      0.007   -135.835      0.000      -0.909      -0.883
ar.L3         -0.3971      0.006    -67.229      0.000      -0.409      -0.385
sigma2         3.7466      0.018    211.623      0.000       3.712       3.781
===================================================================================
Ljung-Box (L1) (Q):                  14.20   Jarque-Bera (JB):           2338363.32
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             3.76
Prob(H) (two-sided):                  0.00   Kurtosis:                       266.93
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.06338, saving model to LSTM2.h5
45/45 - 5s - loss: 0.1377 - accuracy: 0.0000e+00 - val_loss: 0.0634 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 5s/epoch - 110ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.06338 to 0.01627, saving model to LSTM2.h5
45/45 - 0s - loss: 0.0407 - accuracy: 0.0000e+00 - val_loss: 0.0163 - val_accuracy: 0.0037 - lr: 0.0010 - 326ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01627
45/45 - 0s - loss: 0.0241 - accuracy: 0.0000e+00 - val_loss: 0.1140 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 305ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01627
45/45 - 0s - loss: 0.0322 - accuracy: 0.0000e+00 - val_loss: 0.0343 - val_accuracy: 0.0037 - lr: 0.0010 - 316ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01627
45/45 - 0s - loss: 0.0123 - accuracy: 0.0000e+00 - val_loss: 0.0926 - val_accuracy: 0.0037 - lr: 0.0010 - 312ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.01627 to 0.00730, saving model to LSTM2.h5
45/45 - 0s - loss: 0.0156 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 0.0010 - 329ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00730
45/45 - 0s - loss: 0.0048 - accuracy: 0.0000e+00 - val_loss: 0.0354 - val_accuracy: 0.0037 - lr: 0.0010 - 304ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.00730 to 0.00352, saving model to LSTM2.h5
45/45 - 0s - loss: 0.0058 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 0.0010 - 324ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00352
45/45 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0163 - val_accuracy: 0.0037 - lr: 0.0010 - 288ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00352
45/45 - 0s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 0.0010 - 289ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00352
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0114 - val_accuracy: 0.0037 - lr: 0.0010 - 302ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00352
45/45 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 0.0010 - 304ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00013: val_loss did not improve from 0.00352
45/45 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0101 - val_accuracy: 0.0037 - lr: 0.0010 - 316ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00352
45/45 - 0s - loss: 0.0033 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 303ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.7117e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 303ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00352
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 310ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.9463e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 307ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00018: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.8026e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 297ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.3194e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.2077e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 304ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.1439e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 311ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.1094e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 317ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00023: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.0876e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 317ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.0714e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 300ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.0575e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 309ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.0448e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 313ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.0325e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.0203e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 289ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00352
45/45 - 0s - loss: 9.0080e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 300ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.9955e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.9828e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.9699e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 322ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.9566e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 317ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.9432e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 298ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.9294e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 293ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.9154e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 321ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.9011e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 303ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.8866e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 317ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.8718e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 312ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.8567e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 309ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.8414e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 307ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.8258e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.8100e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 308ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.7939e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 298ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.7775e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 309ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.7610e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 306ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.7441e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 306ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.7271e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 289ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.7098e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 316ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.6923e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 307ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.6745e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.6566e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 319ms/epoch - 7ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.6384e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 303ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.6200e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 299ms/epoch - 7ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.6014e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 312ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.5826e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 314ms/epoch - 7ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.5636e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 308ms/epoch - 7ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00352
45/45 - 0s - loss: 8.5444e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 299ms/epoch - 7ms/step
Epoch 00058: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 63.041023819643854 
RMSE:	 7.939837770360541 
MAPE:	 6.449589599500938

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 63.66877348603133 
RMSE:	 7.979271488427457 
MAPE:	 6.567170782771208

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 74.84193590201411 
RMSE:	 8.65112338959595 
MAPE:	 6.92726320779593

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 124.07774757087437 
RMSE:	 11.139019147612341 
MAPE:	 9.962964959911572

KAMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 64.92528911521055 
RMSE:	 8.057623043752454 
MAPE:	 6.682416615913553
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.34 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4212.289, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3747.746, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.17 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3523.401, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3387.759, Time=0.12 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.49 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.64 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3389.758, Time=0.25 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.137 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1689.879
Date:                Sun, 12 Dec 2021   AIC                           3387.759
Time:                        13:29:18   BIC                           3406.522
Sample:                             0   HQIC                          3394.964
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1878      0.003   -345.315      0.000      -1.195      -1.181
ar.L2         -0.8876      0.007   -121.809      0.000      -0.902      -0.873
ar.L3         -0.3957      0.007    -60.127      0.000      -0.409      -0.383
sigma2         3.8904      0.020    193.404      0.000       3.851       3.930
===================================================================================
Ljung-Box (L1) (Q):                  13.21   Jarque-Bera (JB):           1659080.01
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.08   Skew:                             3.28
Prob(H) (two-sided):                  0.00   Kurtosis:                       225.31
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.08475, saving model to LSTM2.h5
58/58 - 5s - loss: 0.1799 - accuracy: 0.0000e+00 - val_loss: 0.0847 - val_accuracy: 0.0037 - lr: 0.0010 - 5s/epoch - 87ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.08475 to 0.00730, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0231 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 0.0010 - 422ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00730
58/58 - 0s - loss: 0.0222 - accuracy: 0.0000e+00 - val_loss: 0.0332 - val_accuracy: 0.0037 - lr: 0.0010 - 399ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00730
58/58 - 0s - loss: 0.0097 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 0.0010 - 404ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00730
58/58 - 0s - loss: 0.0039 - accuracy: 0.0000e+00 - val_loss: 0.0242 - val_accuracy: 0.0037 - lr: 0.0010 - 375ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.00730 to 0.00502, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0084 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 0.0010 - 428ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0042 - accuracy: 0.0000e+00 - val_loss: 0.0159 - val_accuracy: 0.0037 - lr: 0.0010 - 394ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0078 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 0.0010 - 389ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0090 - accuracy: 0.0000e+00 - val_loss: 0.0147 - val_accuracy: 0.0037 - lr: 0.0010 - 397ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0138 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 0.0010 - 382ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0162 - accuracy: 0.0000e+00 - val_loss: 0.0114 - val_accuracy: 0.0037 - lr: 0.0010 - 400ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0227 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 394ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0069 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 383ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 392ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00502
58/58 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 383ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.00502 to 0.00479, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 416ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.00479 to 0.00425, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 424ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.00425 to 0.00389, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 425ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.00389 to 0.00367, saving model to LSTM2.h5
58/58 - 0s - loss: 9.8093e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 416ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.00367 to 0.00355, saving model to LSTM2.h5
58/58 - 0s - loss: 9.5600e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 422ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.00355 to 0.00350, saving model to LSTM2.h5
58/58 - 0s - loss: 9.3938e-04 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 418ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss improved from 0.00350 to 0.00350, saving model to LSTM2.h5
58/58 - 0s - loss: 9.2669e-04 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 407ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00350
58/58 - 0s - loss: 9.1567e-04 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 391ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00350
58/58 - 0s - loss: 9.0528e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 383ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00025: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.9508e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 405ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.9635e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 402ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.5300e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 390ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.3724e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 394ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00350
58/58 - 1s - loss: 8.3141e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 654ms/epoch - 11ms/step
Epoch 30/500

Epoch 00030: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00030: val_loss did not improve from 0.00350
58/58 - 1s - loss: 8.2881e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 669ms/epoch - 12ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.2731e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 378ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.2621e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 403ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.2526e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 376ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.2436e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 377ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.2347e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 385ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.2258e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 384ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.2167e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.2074e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 379ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1978e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 366ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1880e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 395ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1779e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 388ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1676e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1570e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 380ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1462e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 368ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1350e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 385ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1236e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 380ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1119e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.1000e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 405ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.0878e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 375ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.0753e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.0626e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 402ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.0496e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 381ms/epoch - 7ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.0364e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 410ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.0229e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 374ms/epoch - 6ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00350
58/58 - 0s - loss: 8.0091e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 390ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.9951e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 386ms/epoch - 7ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.9809e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 7ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.9664e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 381ms/epoch - 7ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.9517e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 377ms/epoch - 7ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.9368e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 394ms/epoch - 7ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.9216e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 380ms/epoch - 7ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.9062e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 381ms/epoch - 7ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.8907e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 390ms/epoch - 7ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.8749e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 378ms/epoch - 7ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.8589e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 398ms/epoch - 7ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.8427e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 390ms/epoch - 7ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.8264e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 7ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.8098e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 398ms/epoch - 7ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.7932e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 398ms/epoch - 7ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.7763e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 379ms/epoch - 7ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.7593e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 7ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.00350
58/58 - 0s - loss: 7.7422e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 7ms/step
Epoch 00072: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 63.041023819643854 
RMSE:	 7.939837770360541 
MAPE:	 6.449589599500938

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 63.66877348603133 
RMSE:	 7.979271488427457 
MAPE:	 6.567170782771208

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 74.84193590201411 
RMSE:	 8.65112338959595 
MAPE:	 6.92726320779593

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 124.07774757087437 
RMSE:	 11.139019147612341 
MAPE:	 9.962964959911572

KAMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 64.92528911521055 
RMSE:	 8.057623043752454 
MAPE:	 6.682416615913553

MIDPOINT
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 68.19255604013144 
RMSE:	 8.25787842246006 
MAPE:	 6.72839330666561
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.34 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4414.515, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3944.062, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.27 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3715.173, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3577.471, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.03 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.44 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3579.471, Time=0.13 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.401 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1784.736
Date:                Sun, 12 Dec 2021   AIC                           3577.471
Time:                        13:31:04   BIC                           3596.235
Sample:                             0   HQIC                          3584.677
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.844      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.861      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.862      0.000      -0.410      -0.387
sigma2         4.9242      0.023    215.469      0.000       4.879       4.969
===================================================================================
Ljung-Box (L1) (Q):                  14.55   Jarque-Bera (JB):           2468024.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       274.15
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.00805, saving model to LSTM2.h5
43/43 - 5s - loss: 0.1271 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 0.0010 - 5s/epoch - 112ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.00805
43/43 - 0s - loss: 0.0446 - accuracy: 0.0000e+00 - val_loss: 0.0650 - val_accuracy: 0.0037 - lr: 0.0010 - 309ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00805
43/43 - 0s - loss: 0.0053 - accuracy: 0.0000e+00 - val_loss: 0.0155 - val_accuracy: 0.0037 - lr: 0.0010 - 305ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.00805 to 0.00534, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0145 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 0.0010 - 331ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0042 - accuracy: 0.0000e+00 - val_loss: 0.0373 - val_accuracy: 0.0037 - lr: 0.0010 - 301ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0152 - accuracy: 0.0000e+00 - val_loss: 0.0071 - val_accuracy: 0.0037 - lr: 0.0010 - 304ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0082 - accuracy: 0.0000e+00 - val_loss: 0.0773 - val_accuracy: 0.0037 - lr: 0.0010 - 304ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0210 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 0.0010 - 312ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00009: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0082 - accuracy: 0.0000e+00 - val_loss: 0.0732 - val_accuracy: 0.0037 - lr: 0.0010 - 307ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0355 - accuracy: 0.0000e+00 - val_loss: 0.0159 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 302ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0042 - accuracy: 0.0000e+00 - val_loss: 0.0106 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 302ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0034 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 289ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00534
43/43 - 0s - loss: 0.0029 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 312ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.00534 to 0.00493, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0026 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 341ms/epoch - 8ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.00493 to 0.00456, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 315ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.00456 to 0.00445, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 334ms/epoch - 8ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.00445 to 0.00444, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 314ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00444
43/43 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 304ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00444
43/43 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 309ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.00444 to 0.00441, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 329ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.00441 to 0.00433, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 340ms/epoch - 8ms/step
Epoch 22/500

Epoch 00022: val_loss improved from 0.00433 to 0.00424, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 323ms/epoch - 8ms/step
Epoch 23/500

Epoch 00023: val_loss improved from 0.00424 to 0.00413, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 316ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss improved from 0.00413 to 0.00401, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 319ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss improved from 0.00401 to 0.00390, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 330ms/epoch - 8ms/step
Epoch 26/500

Epoch 00026: val_loss improved from 0.00390 to 0.00379, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 320ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss improved from 0.00379 to 0.00369, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 311ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss improved from 0.00369 to 0.00361, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 321ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss improved from 0.00361 to 0.00355, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 335ms/epoch - 8ms/step
Epoch 30/500

Epoch 00030: val_loss improved from 0.00355 to 0.00351, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 310ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss improved from 0.00351 to 0.00349, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 331ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00349
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 293ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00349
43/43 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 290ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00349
43/43 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 290ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00035: val_loss did not improve from 0.00349
43/43 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 289ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00349
43/43 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 285ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.6026e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 280ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.3658e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 299ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.2915e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00040: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.2580e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 283ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.2358e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.2171e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 295ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.1996e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 282ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.1824e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.1651e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 314ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.1475e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.1297e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.1115e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 311ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.0931e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 307ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.0743e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 276ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.0552e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 285ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.0358e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 298ms/epoch - 7ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00349
43/43 - 0s - loss: 9.0161e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 292ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.9960e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 291ms/epoch - 7ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.9756e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 298ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.9550e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 290ms/epoch - 7ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.9340e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 294ms/epoch - 7ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.9127e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 303ms/epoch - 7ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.8911e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 280ms/epoch - 7ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.8693e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 300ms/epoch - 7ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.8471e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 308ms/epoch - 7ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.8247e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 294ms/epoch - 7ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.8021e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 286ms/epoch - 7ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.7792e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.7560e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 301ms/epoch - 7ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.7326e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 283ms/epoch - 7ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.7091e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.6853e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 7ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.6613e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 7ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.6371e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 284ms/epoch - 7ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.6128e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 277ms/epoch - 6ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.5883e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 7ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.5637e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 7ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.5389e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 293ms/epoch - 7ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.5141e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 7ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.4891e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 292ms/epoch - 7ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.4640e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 289ms/epoch - 7ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.4388e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 293ms/epoch - 7ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.4136e-04 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 291ms/epoch - 7ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.3883e-04 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 295ms/epoch - 7ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.00349
43/43 - 0s - loss: 8.3630e-04 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 297ms/epoch - 7ms/step
Epoch 00081: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 63.041023819643854 
RMSE:	 7.939837770360541 
MAPE:	 6.449589599500938

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 63.66877348603133 
RMSE:	 7.979271488427457 
MAPE:	 6.567170782771208

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 74.84193590201411 
RMSE:	 8.65112338959595 
MAPE:	 6.92726320779593

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 124.07774757087437 
RMSE:	 11.139019147612341 
MAPE:	 9.962964959911572

KAMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 64.92528911521055 
RMSE:	 8.057623043752454 
MAPE:	 6.682416615913553

MIDPOINT
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 68.19255604013144 
RMSE:	 8.25787842246006 
MAPE:	 6.72839330666561

T3
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 149.0300312328299 
RMSE:	 12.207785680983669 
MAPE:	 10.094975187792123
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4352.703, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3889.412, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.19 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3689.930, Time=0.04 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3574.245, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.35 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.62 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3576.245, Time=0.14 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.858 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1783.123
Date:                Sun, 12 Dec 2021   AIC                           3574.245
Time:                        13:32:42   BIC                           3593.008
Sample:                             0   HQIC                          3581.451
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1480      0.004   -302.430      0.000      -1.155      -1.141
ar.L2         -0.8300      0.008    -99.682      0.000      -0.846      -0.814
ar.L3         -0.3687      0.007    -50.527      0.000      -0.383      -0.354
sigma2         4.9055      0.028    175.970      0.000       4.851       4.960
===================================================================================
Ljung-Box (L1) (Q):                  11.61   Jarque-Bera (JB):           1261976.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.16   Skew:                             2.52
Prob(H) (two-sided):                  0.00   Kurtosis:                       196.90
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.07399, saving model to LSTM2.h5
90/90 - 6s - loss: 0.1376 - accuracy: 0.0000e+00 - val_loss: 0.0740 - val_accuracy: 0.0037 - lr: 0.0010 - 6s/epoch - 64ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.07399 to 0.01692, saving model to LSTM2.h5
90/90 - 1s - loss: 0.0319 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 0.0010 - 599ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01692
90/90 - 1s - loss: 0.0548 - accuracy: 0.0000e+00 - val_loss: 0.0262 - val_accuracy: 0.0037 - lr: 0.0010 - 567ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.01692 to 0.01084, saving model to LSTM2.h5
90/90 - 1s - loss: 0.0325 - accuracy: 0.0000e+00 - val_loss: 0.0108 - val_accuracy: 0.0037 - lr: 0.0010 - 608ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.01084 to 0.01009, saving model to LSTM2.h5
90/90 - 1s - loss: 0.0231 - accuracy: 0.0000e+00 - val_loss: 0.0101 - val_accuracy: 0.0037 - lr: 0.0010 - 586ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.01009 to 0.00743, saving model to LSTM2.h5
90/90 - 1s - loss: 0.0143 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 0.0010 - 613ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00743
90/90 - 1s - loss: 0.0090 - accuracy: 0.0000e+00 - val_loss: 0.0118 - val_accuracy: 0.0037 - lr: 0.0010 - 572ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00743
90/90 - 1s - loss: 0.0083 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 0.0010 - 568ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00743
90/90 - 1s - loss: 0.0077 - accuracy: 0.0000e+00 - val_loss: 0.0198 - val_accuracy: 0.0037 - lr: 0.0010 - 568ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00743
90/90 - 1s - loss: 0.0090 - accuracy: 0.0000e+00 - val_loss: 0.0111 - val_accuracy: 0.0037 - lr: 0.0010 - 568ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.00743
90/90 - 1s - loss: 0.0095 - accuracy: 0.0000e+00 - val_loss: 0.0270 - val_accuracy: 0.0037 - lr: 0.0010 - 567ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.00743 to 0.00655, saving model to LSTM2.h5
90/90 - 1s - loss: 0.0199 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 608ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0037 - accuracy: 0.0000e+00 - val_loss: 0.0068 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 580ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0025 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 592ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 597ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0097 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 583ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00017: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0111 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 575ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0114 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 580ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0116 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 564ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0118 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 589ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0120 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 582ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00022: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0122 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 570ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00655
90/90 - 1s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0124 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 592ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.9328e-04 - accuracy: 0.0000e+00 - val_loss: 0.0125 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 586ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.8587e-04 - accuracy: 0.0000e+00 - val_loss: 0.0127 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 602ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.7856e-04 - accuracy: 0.0000e+00 - val_loss: 0.0129 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 590ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.7137e-04 - accuracy: 0.0000e+00 - val_loss: 0.0131 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 576ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.6430e-04 - accuracy: 0.0000e+00 - val_loss: 0.0132 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 578ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.5736e-04 - accuracy: 0.0000e+00 - val_loss: 0.0134 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 572ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.5055e-04 - accuracy: 0.0000e+00 - val_loss: 0.0136 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 590ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.4388e-04 - accuracy: 0.0000e+00 - val_loss: 0.0138 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 574ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.3736e-04 - accuracy: 0.0000e+00 - val_loss: 0.0140 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 588ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.3099e-04 - accuracy: 0.0000e+00 - val_loss: 0.0143 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 590ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.2477e-04 - accuracy: 0.0000e+00 - val_loss: 0.0145 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 585ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.1871e-04 - accuracy: 0.0000e+00 - val_loss: 0.0147 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 587ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.1281e-04 - accuracy: 0.0000e+00 - val_loss: 0.0149 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 579ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.0706e-04 - accuracy: 0.0000e+00 - val_loss: 0.0152 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 578ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00655
90/90 - 1s - loss: 9.0146e-04 - accuracy: 0.0000e+00 - val_loss: 0.0154 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 580ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.9602e-04 - accuracy: 0.0000e+00 - val_loss: 0.0156 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 594ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.9072e-04 - accuracy: 0.0000e+00 - val_loss: 0.0159 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 571ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.8556e-04 - accuracy: 0.0000e+00 - val_loss: 0.0161 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 587ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.8054e-04 - accuracy: 0.0000e+00 - val_loss: 0.0164 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 581ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.7565e-04 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 589ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.7090e-04 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 587ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.6627e-04 - accuracy: 0.0000e+00 - val_loss: 0.0171 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 576ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.6176e-04 - accuracy: 0.0000e+00 - val_loss: 0.0173 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 571ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.5737e-04 - accuracy: 0.0000e+00 - val_loss: 0.0176 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 578ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.5310e-04 - accuracy: 0.0000e+00 - val_loss: 0.0178 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 552ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.4894e-04 - accuracy: 0.0000e+00 - val_loss: 0.0180 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 579ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.4488e-04 - accuracy: 0.0000e+00 - val_loss: 0.0182 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 577ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.4094e-04 - accuracy: 0.0000e+00 - val_loss: 0.0185 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 589ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.3710e-04 - accuracy: 0.0000e+00 - val_loss: 0.0187 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 574ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.3336e-04 - accuracy: 0.0000e+00 - val_loss: 0.0189 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 560ms/epoch - 6ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.2972e-04 - accuracy: 0.0000e+00 - val_loss: 0.0191 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 560ms/epoch - 6ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.2619e-04 - accuracy: 0.0000e+00 - val_loss: 0.0193 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 563ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.2275e-04 - accuracy: 0.0000e+00 - val_loss: 0.0195 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 593ms/epoch - 7ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.1941e-04 - accuracy: 0.0000e+00 - val_loss: 0.0197 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 570ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.1617e-04 - accuracy: 0.0000e+00 - val_loss: 0.0198 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 608ms/epoch - 7ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.1303e-04 - accuracy: 0.0000e+00 - val_loss: 0.0200 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 578ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.0998e-04 - accuracy: 0.0000e+00 - val_loss: 0.0202 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 592ms/epoch - 7ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.0702e-04 - accuracy: 0.0000e+00 - val_loss: 0.0203 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 569ms/epoch - 6ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00655
90/90 - 1s - loss: 8.0415e-04 - accuracy: 0.0000e+00 - val_loss: 0.0205 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 561ms/epoch - 6ms/step
Epoch 00062: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 63.041023819643854 
RMSE:	 7.939837770360541 
MAPE:	 6.449589599500938

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 63.66877348603133 
RMSE:	 7.979271488427457 
MAPE:	 6.567170782771208

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 74.84193590201411 
RMSE:	 8.65112338959595 
MAPE:	 6.92726320779593

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 124.07774757087437 
RMSE:	 11.139019147612341 
MAPE:	 9.962964959911572

KAMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 64.92528911521055 
RMSE:	 8.057623043752454 
MAPE:	 6.682416615913553

MIDPOINT
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 68.19255604013144 
RMSE:	 8.25787842246006 
MAPE:	 6.72839330666561

T3
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 149.0300312328299 
RMSE:	 12.207785680983669 
MAPE:	 10.094975187792123

TEMA
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 71.80641753112648 
RMSE:	 8.473866740227066 
MAPE:	 7.512371017185029
Runtime: mins: 12.728734250049998

Architecture Used

In [ ]:
from google.colab import files
import cv2
uploaded = files.upload()
Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to enable. 
Saving Experiment2.png to Experiment2 (1).png
In [ ]:
img = cv2.imread('Experiment2.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)
Out[ ]:
<matplotlib.image.AxesImage at 0x7fb3f66e72d0>

Model Plots

In [99]:
with open('simulation2_data.json') as json_file:
    simulation2 = json.load(json_file)
fileimg = 'Experiment2'
In [100]:
for i in range(len(list(simulation2.keys()))):
  SIM = list(simulation2.keys())[i]
  plot_train(simulation2,SIM)
  plot_test(simulation2,SIM)

----- Train RMSE for SMA ----- 8.825487281603085
----- Train_MSE_LSTM for SMA ----- 77.88922575773782
----- Train MAE LSTM for SMA ----- 7.678486704575587

----- Test RMSE for SMA----- 7.939837770360541
----- Test_MSE_LSTM for SMA----- 63.041023819643854
----- Test_MAE_LSTM for SMA----- 6.449589599500938

----- Train RMSE for EMA ----- 10.17885992167541
----- Train_MSE_LSTM for EMA ----- 103.60918930508994
----- Train MAE LSTM for EMA ----- 9.004301877044565

----- Test RMSE for EMA----- 7.979271488427457
----- Test_MSE_LSTM for EMA----- 63.66877348603133
----- Test_MAE_LSTM for EMA----- 6.567170782771208

----- Train RMSE for WMA ----- 10.465802137903177
----- Train_MSE_LSTM for WMA ----- 109.5330143897387
----- Train MAE LSTM for WMA ----- 9.31366489027537

----- Test RMSE for WMA----- 8.65112338959595
----- Test_MSE_LSTM for WMA----- 74.84193590201411
----- Test_MAE_LSTM for WMA----- 6.92726320779593

----- Train RMSE for DEMA ----- 12.116566242192249
----- Train_MSE_LSTM for DEMA ----- 146.8111775014328
----- Train MAE LSTM for DEMA ----- 10.867763409922118

----- Test RMSE for DEMA----- 11.139019147612341
----- Test_MSE_LSTM for DEMA----- 124.07774757087437
----- Test_MAE_LSTM for DEMA----- 9.962964959911572

----- Train RMSE for KAMA ----- 10.526385532586437
----- Train_MSE_LSTM for KAMA ----- 110.80479238064504
----- Train MAE LSTM for KAMA ----- 9.464160976428907

----- Test RMSE for KAMA----- 8.057623043752454
----- Test_MSE_LSTM for KAMA----- 64.92528911521055
----- Test_MAE_LSTM for KAMA----- 6.682416615913553

----- Train RMSE for MIDPOINT ----- 9.44780598788214
----- Train_MSE_LSTM for MIDPOINT ----- 89.26103798466161
----- Train MAE LSTM for MIDPOINT ----- 8.392066648593033

----- Test RMSE for MIDPOINT----- 8.25787842246006
----- Test_MSE_LSTM for MIDPOINT----- 68.19255604013144
----- Test_MAE_LSTM for MIDPOINT----- 6.72839330666561

----- Train RMSE for T3 ----- 12.031116618105388
----- Train_MSE_LSTM for T3 ----- 144.74776707845163
----- Train MAE LSTM for T3 ----- 10.821733970313776

----- Test RMSE for T3----- 12.207785680983669
----- Test_MSE_LSTM for T3----- 149.0300312328299
----- Test_MAE_LSTM for T3----- 10.094975187792123

----- Train RMSE for TEMA ----- 7.432502353073835
----- Train_MSE_LSTM for TEMA ----- 55.242091228448096
----- Train MAE LSTM for TEMA ----- 5.1691971761128395

----- Test RMSE for TEMA----- 8.473866740227066
----- Test_MSE_LSTM for TEMA----- 71.80641753112648
----- Test_MAE_LSTM for TEMA----- 7.512371017185029

Univariate Arima Multistep MutiVariate LSTM Hybrid Model Experiment 3

In [ ]:
def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # # Option 1
    # # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()




    # Option 3
    # define custom activation
    # 
    class Double_Tanh(Activation):
        def __init__(self, activation, **kwargs):
            super(Double_Tanh, self).__init__(activation, **kwargs)
            self.__name__ = 'double_tanh'

    def double_tanh(x):
        return (K.tanh(x) * 2)

    get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
        # Model Generation
    model = Sequential()
    #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    model.add(Dense(1))
    model.add(Activation(double_tanh))
    model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM3.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te
In [ ]:
if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation3 = {}
    imgfile = 'Experiment3'
    for ma in optimized_period:
              print(ma)
              print(functions[ma])
              print ( int( optimized_period[ma]))
            # if ma == 'SMA':
              low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
              low_vol = low_vol.fillna(0)
              low_vol_data = df['close']
              high_vol = pd.DataFrame()
              df2 = df.copy()
              for i in df2.columns:
                if i in low_vol.columns:
                  high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
              high_vol_data = df['close']
              ## *****************************************************
              # Generate ARIMA and LSTM predictions
              print('\nWorking on ' + ma + ' predictions')
              try:
                print('parameters used : ', train_len, test_len)
                low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima(low_vol,low_vol_data, train_len, test_len)
              except:
                  print('ARIMA error, skipping to next MA type')
                  continue
              Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
              final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
              mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
              rmse_ftr = mse_ftr ** 0.5
              mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
              mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

              final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
              mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
              rmse = mse ** 0.5
              mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              # Generate prediction accuracy
              actual = df['close'].tail(test_len).values
              result_1 = []
              result_2 = []
              for i in range(1, len(final_prediction)):
                  # Compare prediction to previous close price
                  if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                      result_1.append(1)
                  elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                      result_1.append(1)
                  else:
                      result_1.append(0)

                  # Compare prediction to previous prediction
                  if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                      result_2.append(1)
                  elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                      result_2.append(1)
                  else:
                      result_2.append(0)

              accuracy_1 = np.mean(result_1)
              accuracy_2 = np.mean(result_2)

              simulation3[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                            'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                            'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                            'rmse': rmse_ftr, 'mae' : mae_ftr},
                                'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                          'rmse': rmse, 'mae': mae },
                                'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

              # save simulation data here as checkpoint
              with open('simulation3_data.json', 'w') as fp:
                  json.dump(simulation3, fp)

              for ma in simulation3.keys():
                  print('\n' + ma)
                  print('Prediction vs Close:\t\t' + str(round(100*simulation3[ma]['accuracy']['prediction vs close'], 2))
                        + '% Accuracy')
                  print('Prediction vs Prediction:\t' + str(round(100*simulation3[ma]['accuracy']['prediction vs prediction'], 2))
                        + '% Accuracy')
                  print('MSE:\t', simulation3[ma]['final']['mse'],
                        '\nRMSE:\t', simulation3[ma]['final']['rmse'],
                        '\nMAPE:\t', simulation3[ma]['final']['mae'])#,
                        # '\nMAPE:\t', simulation[ma]['final']['mape'])
            # else:
            #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.39 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4157.020, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3687.148, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.13 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3458.651, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3322.133, Time=0.06 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.53 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.53 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3324.133, Time=0.14 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 1.919 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1657.067
Date:                Sun, 12 Dec 2021   AIC                           3322.133
Time:                        13:38:00   BIC                           3340.897
Sample:                             0   HQIC                          3329.339
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1966      0.003   -387.226      0.000      -1.203      -1.191
ar.L2         -0.8952      0.006   -138.692      0.000      -0.908      -0.883
ar.L3         -0.3968      0.006    -68.284      0.000      -0.408      -0.385
sigma2         3.5858      0.017    214.535      0.000       3.553       3.619
===================================================================================
Ljung-Box (L1) (Q):                  14.47   Jarque-Bera (JB):           2428881.42
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       271.99
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04037, saving model to LSTM3.h5
48/48 - 3s - loss: 0.1177 - mse: 0.1177 - mae: 0.2555 - val_loss: 0.0404 - val_mse: 0.0404 - val_mae: 0.1495 - lr: 0.0010 - 3s/epoch - 60ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.04037 to 0.02521, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0329 - mse: 0.0329 - mae: 0.1399 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1348 - lr: 0.0010 - 267ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.02521 to 0.02239, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0141 - mse: 0.0141 - mae: 0.0945 - val_loss: 0.0224 - val_mse: 0.0224 - val_mae: 0.1237 - lr: 0.0010 - 278ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.02239 to 0.02012, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0135 - mse: 0.0135 - mae: 0.0916 - val_loss: 0.0201 - val_mse: 0.0201 - val_mae: 0.1179 - lr: 0.0010 - 276ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.02012 to 0.01903, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0107 - mse: 0.0107 - mae: 0.0801 - val_loss: 0.0190 - val_mse: 0.0190 - val_mae: 0.1147 - lr: 0.0010 - 269ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.01903 to 0.01707, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0832 - val_loss: 0.0171 - val_mse: 0.0171 - val_mae: 0.1061 - lr: 0.0010 - 268ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.01707 to 0.01650, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0797 - val_loss: 0.0165 - val_mse: 0.0165 - val_mae: 0.1035 - lr: 0.0010 - 273ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01650
48/48 - 0s - loss: 0.0100 - mse: 0.0100 - mae: 0.0778 - val_loss: 0.0171 - val_mse: 0.0171 - val_mae: 0.1053 - lr: 0.0010 - 254ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.01650 to 0.01619, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0106 - mse: 0.0106 - mae: 0.0779 - val_loss: 0.0162 - val_mse: 0.0162 - val_mae: 0.1009 - lr: 0.0010 - 286ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.01619 to 0.01583, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0816 - val_loss: 0.0158 - val_mse: 0.0158 - val_mae: 0.0985 - lr: 0.0010 - 270ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0114 - mse: 0.0114 - mae: 0.0806 - val_loss: 0.0161 - val_mse: 0.0161 - val_mae: 0.1000 - lr: 0.0010 - 266ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0137 - mse: 0.0137 - mae: 0.0904 - val_loss: 0.0185 - val_mse: 0.0185 - val_mae: 0.1076 - lr: 0.0010 - 252ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0125 - mse: 0.0125 - mae: 0.0870 - val_loss: 0.0161 - val_mse: 0.0161 - val_mae: 0.0982 - lr: 0.0010 - 254ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0152 - mse: 0.0152 - mae: 0.0966 - val_loss: 0.0162 - val_mse: 0.0162 - val_mae: 0.0984 - lr: 0.0010 - 258ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00015: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0174 - mse: 0.0174 - mae: 0.1047 - val_loss: 0.0170 - val_mse: 0.0170 - val_mae: 0.1009 - lr: 0.0010 - 253ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0336 - mse: 0.0336 - mae: 0.1509 - val_loss: 0.0255 - val_mse: 0.0255 - val_mae: 0.1273 - lr: 1.0000e-04 - 249ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0881 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1368 - lr: 1.0000e-04 - 249ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0085 - mse: 0.0085 - mae: 0.0760 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1351 - lr: 1.0000e-04 - 260ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0726 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1324 - lr: 1.0000e-04 - 260ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00020: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0727 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1315 - lr: 1.0000e-04 - 253ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0651 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1316 - lr: 1.0000e-05 - 254ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0659 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1318 - lr: 1.0000e-05 - 273ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0659 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1318 - lr: 1.0000e-05 - 253ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0678 - val_loss: 0.0270 - val_mse: 0.0270 - val_mae: 0.1320 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00025: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0653 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1317 - lr: 1.0000e-05 - 250ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0658 - val_loss: 0.0268 - val_mse: 0.0268 - val_mae: 0.1316 - lr: 1.0000e-05 - 264ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0656 - val_loss: 0.0268 - val_mse: 0.0268 - val_mae: 0.1315 - lr: 1.0000e-05 - 247ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0660 - val_loss: 0.0268 - val_mse: 0.0268 - val_mae: 0.1316 - lr: 1.0000e-05 - 256ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0676 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1313 - lr: 1.0000e-05 - 254ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0653 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1312 - lr: 1.0000e-05 - 263ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0680 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1311 - lr: 1.0000e-05 - 254ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0654 - val_loss: 0.0266 - val_mse: 0.0266 - val_mae: 0.1308 - lr: 1.0000e-05 - 269ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0659 - val_loss: 0.0265 - val_mse: 0.0265 - val_mae: 0.1307 - lr: 1.0000e-05 - 253ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0648 - val_loss: 0.0264 - val_mse: 0.0264 - val_mae: 0.1304 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0634 - val_loss: 0.0263 - val_mse: 0.0263 - val_mae: 0.1300 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0652 - val_loss: 0.0261 - val_mse: 0.0261 - val_mae: 0.1295 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0631 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1291 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0634 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1290 - lr: 1.0000e-05 - 259ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0644 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1287 - lr: 1.0000e-05 - 252ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0611 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1283 - lr: 1.0000e-05 - 257ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0652 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1285 - lr: 1.0000e-05 - 253ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0638 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1281 - lr: 1.0000e-05 - 248ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0622 - val_loss: 0.0255 - val_mse: 0.0255 - val_mae: 0.1276 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0651 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1271 - lr: 1.0000e-05 - 260ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0641 - val_loss: 0.0253 - val_mse: 0.0253 - val_mae: 0.1270 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0640 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1265 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0621 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1264 - lr: 1.0000e-05 - 267ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0643 - val_loss: 0.0250 - val_mse: 0.0250 - val_mae: 0.1261 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0627 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1258 - lr: 1.0000e-05 - 265ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0615 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1257 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0633 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1253 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0628 - val_loss: 0.0246 - val_mse: 0.0246 - val_mae: 0.1250 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0615 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1240 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0635 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1237 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0613 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1234 - lr: 1.0000e-05 - 247ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0611 - val_loss: 0.0240 - val_mse: 0.0240 - val_mae: 0.1231 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0615 - val_loss: 0.0240 - val_mse: 0.0240 - val_mae: 0.1230 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0624 - val_loss: 0.0238 - val_mse: 0.0238 - val_mae: 0.1226 - lr: 1.0000e-05 - 254ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0629 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1221 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01583
48/48 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0610 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1216 - lr: 1.0000e-05 - 259ms/epoch - 5ms/step
Epoch 00060: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 123.96893050522607 
RMSE:	 11.134133576764116 
MAPE:	 9.602398807260117
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4231.556, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3761.238, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.21 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3532.227, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3394.496, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.59 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.45 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3396.496, Time=0.15 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 1.966 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1693.248
Date:                Sun, 12 Dec 2021   AIC                           3394.496
Time:                        13:39:39   BIC                           3413.260
Sample:                             0   HQIC                          3401.702
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.569      0.000      -1.204      -1.192
ar.L2         -0.8976      0.006   -139.811      0.000      -0.910      -0.885
ar.L3         -0.3984      0.006    -68.662      0.000      -0.410      -0.387
sigma2         3.9230      0.018    215.372      0.000       3.887       3.959
===================================================================================
Ljung-Box (L1) (Q):                  14.54   Jarque-Bera (JB):           2462173.05
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.82
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.01660, saving model to LSTM3.h5
16/16 - 3s - loss: 0.0665 - mse: 0.0665 - mae: 0.2195 - val_loss: 0.0166 - val_mse: 0.0166 - val_mae: 0.1016 - lr: 0.0010 - 3s/epoch - 184ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.01660 to 0.01641, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0214 - mse: 0.0214 - mae: 0.1140 - val_loss: 0.0164 - val_mse: 0.0164 - val_mae: 0.0972 - lr: 0.0010 - 121ms/epoch - 8ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01641
16/16 - 0s - loss: 0.0122 - mse: 0.0122 - mae: 0.0864 - val_loss: 0.0188 - val_mse: 0.0188 - val_mae: 0.1073 - lr: 0.0010 - 107ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01641
16/16 - 0s - loss: 0.0113 - mse: 0.0113 - mae: 0.0848 - val_loss: 0.0198 - val_mse: 0.0198 - val_mae: 0.1103 - lr: 0.0010 - 97ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.01641 to 0.01552, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0102 - mse: 0.0102 - mae: 0.0792 - val_loss: 0.0155 - val_mse: 0.0155 - val_mae: 0.0939 - lr: 0.0010 - 123ms/epoch - 8ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.01552 to 0.01419, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0094 - mse: 0.0094 - mae: 0.0758 - val_loss: 0.0142 - val_mse: 0.0142 - val_mae: 0.0887 - lr: 0.0010 - 123ms/epoch - 8ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01419
16/16 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0730 - val_loss: 0.0145 - val_mse: 0.0145 - val_mae: 0.0894 - lr: 0.0010 - 113ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.01419 to 0.01396, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0680 - val_loss: 0.0140 - val_mse: 0.0140 - val_mae: 0.0879 - lr: 0.0010 - 118ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.01396 to 0.01391, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0691 - val_loss: 0.0139 - val_mse: 0.0139 - val_mae: 0.0877 - lr: 0.0010 - 118ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.01391 to 0.01358, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0689 - val_loss: 0.0136 - val_mse: 0.0136 - val_mae: 0.0869 - lr: 0.0010 - 121ms/epoch - 8ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.01358 to 0.01304, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0636 - val_loss: 0.0130 - val_mse: 0.0130 - val_mae: 0.0859 - lr: 0.0010 - 117ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.01304 to 0.01294, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0644 - val_loss: 0.0129 - val_mse: 0.0129 - val_mae: 0.0852 - lr: 0.0010 - 118ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.01294 to 0.01271, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0643 - val_loss: 0.0127 - val_mse: 0.0127 - val_mae: 0.0849 - lr: 0.0010 - 113ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0616 - val_loss: 0.0129 - val_mse: 0.0129 - val_mae: 0.0873 - lr: 0.0010 - 101ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0578 - val_loss: 0.0140 - val_mse: 0.0140 - val_mae: 0.0942 - lr: 0.0010 - 110ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.0132 - val_mse: 0.0132 - val_mae: 0.0907 - lr: 0.0010 - 116ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0580 - val_loss: 0.0140 - val_mse: 0.0140 - val_mae: 0.0959 - lr: 0.0010 - 104ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00018: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0650 - val_loss: 0.0141 - val_mse: 0.0141 - val_mae: 0.0969 - lr: 0.0010 - 107ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0544 - val_loss: 0.0139 - val_mse: 0.0139 - val_mae: 0.0959 - lr: 1.0000e-04 - 102ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0513 - val_loss: 0.0138 - val_mse: 0.0138 - val_mae: 0.0951 - lr: 1.0000e-04 - 96ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0545 - val_loss: 0.0140 - val_mse: 0.0140 - val_mae: 0.0959 - lr: 1.0000e-04 - 101ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0502 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0974 - lr: 1.0000e-04 - 98ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00023: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0511 - val_loss: 0.0146 - val_mse: 0.0146 - val_mae: 0.0986 - lr: 1.0000e-04 - 101ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0511 - val_loss: 0.0145 - val_mse: 0.0145 - val_mae: 0.0986 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0521 - val_loss: 0.0145 - val_mse: 0.0145 - val_mae: 0.0985 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0508 - val_loss: 0.0145 - val_mse: 0.0145 - val_mae: 0.0985 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0518 - val_loss: 0.0145 - val_mse: 0.0145 - val_mae: 0.0985 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00028: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0519 - val_loss: 0.0145 - val_mse: 0.0145 - val_mae: 0.0983 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0519 - val_loss: 0.0145 - val_mse: 0.0145 - val_mae: 0.0982 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0547 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0980 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0502 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0980 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0504 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0980 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0513 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0981 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0480 - val_loss: 0.0145 - val_mse: 0.0145 - val_mae: 0.0982 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0487 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0981 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0980 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0528 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0980 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0537 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0979 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0500 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0979 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0495 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0980 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0509 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0980 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0504 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0981 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0495 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0979 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0504 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0979 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0522 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0979 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0524 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0979 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0513 - val_loss: 0.0144 - val_mse: 0.0144 - val_mae: 0.0978 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0517 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0977 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0515 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0975 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0520 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0975 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0512 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0975 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0510 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0974 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0973 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0510 - val_loss: 0.0142 - val_mse: 0.0142 - val_mae: 0.0972 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0518 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0973 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0500 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0973 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0518 - val_loss: 0.0142 - val_mse: 0.0142 - val_mae: 0.0972 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0525 - val_loss: 0.0142 - val_mse: 0.0142 - val_mae: 0.0972 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0500 - val_loss: 0.0142 - val_mse: 0.0142 - val_mae: 0.0972 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0974 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0504 - val_loss: 0.0143 - val_mse: 0.0143 - val_mae: 0.0974 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0500 - val_loss: 0.0142 - val_mse: 0.0142 - val_mae: 0.0973 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.01271
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0500 - val_loss: 0.0142 - val_mse: 0.0142 - val_mae: 0.0971 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 00063: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 123.96893050522607 
RMSE:	 11.134133576764116 
MAPE:	 9.602398807260117

EMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 63.919262026708296 
RMSE:	 7.994952284204596 
MAPE:	 6.479287961204322
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4264.089, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3793.930, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.19 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3564.923, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3427.258, Time=0.11 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.57 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.40 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3429.258, Time=0.24 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.976 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1709.629
Date:                Sun, 12 Dec 2021   AIC                           3427.258
Time:                        13:41:09   BIC                           3446.021
Sample:                             0   HQIC                          3434.464
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1981      0.003   -389.386      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.699      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.737      0.000      -0.410      -0.387
sigma2         4.0860      0.019    215.311      0.000       4.049       4.123
===================================================================================
Ljung-Box (L1) (Q):                  14.57   Jarque-Bera (JB):           2460901.70
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.75
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.37726, saving model to LSTM3.h5
17/17 - 3s - loss: 0.1493 - mse: 0.1493 - mae: 0.2969 - val_loss: 0.3773 - val_mse: 0.3773 - val_mae: 0.5672 - lr: 0.0010 - 3s/epoch - 195ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.37726
17/17 - 0s - loss: 0.0305 - mse: 0.0305 - mae: 0.1451 - val_loss: 0.3820 - val_mse: 0.3820 - val_mae: 0.5742 - lr: 0.0010 - 109ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.37726 to 0.27295, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0286 - mse: 0.0286 - mae: 0.1379 - val_loss: 0.2729 - val_mse: 0.2729 - val_mae: 0.4756 - lr: 0.0010 - 134ms/epoch - 8ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.27295 to 0.25856, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0158 - mse: 0.0158 - mae: 0.1020 - val_loss: 0.2586 - val_mse: 0.2586 - val_mae: 0.4621 - lr: 0.0010 - 135ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.25856 to 0.23338, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0145 - mse: 0.0145 - mae: 0.0954 - val_loss: 0.2334 - val_mse: 0.2334 - val_mae: 0.4355 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.23338 to 0.23136, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0120 - mse: 0.0120 - mae: 0.0873 - val_loss: 0.2314 - val_mse: 0.2314 - val_mae: 0.4337 - lr: 0.0010 - 120ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.23136 to 0.21178, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0135 - mse: 0.0135 - mae: 0.0899 - val_loss: 0.2118 - val_mse: 0.2118 - val_mae: 0.4123 - lr: 0.0010 - 129ms/epoch - 8ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.21178 to 0.20067, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0115 - mse: 0.0115 - mae: 0.0855 - val_loss: 0.2007 - val_mse: 0.2007 - val_mae: 0.4003 - lr: 0.0010 - 129ms/epoch - 8ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.20067 to 0.19406, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0828 - val_loss: 0.1941 - val_mse: 0.1941 - val_mae: 0.3929 - lr: 0.0010 - 130ms/epoch - 8ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.19406
17/17 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0747 - val_loss: 0.1976 - val_mse: 0.1976 - val_mae: 0.3976 - lr: 0.0010 - 105ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.19406 to 0.17274, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0093 - mse: 0.0093 - mae: 0.0751 - val_loss: 0.1727 - val_mse: 0.1727 - val_mae: 0.3674 - lr: 0.0010 - 121ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.17274
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0698 - val_loss: 0.1760 - val_mse: 0.1760 - val_mae: 0.3719 - lr: 0.0010 - 101ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.17274 to 0.17002, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0661 - val_loss: 0.1700 - val_mse: 0.1700 - val_mae: 0.3648 - lr: 0.0010 - 116ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.17002 to 0.15280, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0697 - val_loss: 0.1528 - val_mse: 0.1528 - val_mae: 0.3426 - lr: 0.0010 - 120ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.15280 to 0.13889, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0683 - val_loss: 0.1389 - val_mse: 0.1389 - val_mae: 0.3234 - lr: 0.0010 - 134ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.13889
17/17 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0640 - val_loss: 0.1452 - val_mse: 0.1452 - val_mae: 0.3326 - lr: 0.0010 - 113ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.13889
17/17 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0657 - val_loss: 0.1470 - val_mse: 0.1470 - val_mae: 0.3351 - lr: 0.0010 - 113ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.13889
17/17 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0587 - val_loss: 0.1411 - val_mse: 0.1411 - val_mae: 0.3272 - lr: 0.0010 - 107ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.13889 to 0.12895, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0611 - val_loss: 0.1290 - val_mse: 0.1290 - val_mae: 0.3102 - lr: 0.0010 - 122ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.12895 to 0.11477, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0606 - val_loss: 0.1148 - val_mse: 0.1148 - val_mae: 0.2885 - lr: 0.0010 - 121ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.11477
17/17 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0603 - val_loss: 0.1149 - val_mse: 0.1149 - val_mae: 0.2886 - lr: 0.0010 - 113ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.11477
17/17 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0562 - val_loss: 0.1246 - val_mse: 0.1246 - val_mae: 0.3042 - lr: 0.0010 - 103ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss improved from 0.11477 to 0.11461, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0565 - val_loss: 0.1146 - val_mse: 0.1146 - val_mae: 0.2897 - lr: 0.0010 - 126ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss improved from 0.11461 to 0.10943, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0594 - val_loss: 0.1094 - val_mse: 0.1094 - val_mae: 0.2816 - lr: 0.0010 - 137ms/epoch - 8ms/step
Epoch 25/500

Epoch 00025: val_loss improved from 0.10943 to 0.10647, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0571 - val_loss: 0.1065 - val_mse: 0.1065 - val_mae: 0.2772 - lr: 0.0010 - 132ms/epoch - 8ms/step
Epoch 26/500

Epoch 00026: val_loss improved from 0.10647 to 0.10282, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0567 - val_loss: 0.1028 - val_mse: 0.1028 - val_mae: 0.2715 - lr: 0.0010 - 120ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.10282
17/17 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0569 - val_loss: 0.1031 - val_mse: 0.1031 - val_mae: 0.2718 - lr: 0.0010 - 102ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.10282
17/17 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0562 - val_loss: 0.1061 - val_mse: 0.1061 - val_mae: 0.2768 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss improved from 0.10282 to 0.10251, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0543 - val_loss: 0.1025 - val_mse: 0.1025 - val_mae: 0.2717 - lr: 0.0010 - 122ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss improved from 0.10251 to 0.10194, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0549 - val_loss: 0.1019 - val_mse: 0.1019 - val_mae: 0.2717 - lr: 0.0010 - 125ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss improved from 0.10194 to 0.09181, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0569 - val_loss: 0.0918 - val_mse: 0.0918 - val_mae: 0.2546 - lr: 0.0010 - 131ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss improved from 0.09181 to 0.08485, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0549 - val_loss: 0.0849 - val_mse: 0.0849 - val_mae: 0.2426 - lr: 0.0010 - 132ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.08485
17/17 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0560 - val_loss: 0.0945 - val_mse: 0.0945 - val_mae: 0.2598 - lr: 0.0010 - 114ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss improved from 0.08485 to 0.08199, saving model to LSTM3.h5
17/17 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.0820 - val_mse: 0.0820 - val_mae: 0.2378 - lr: 0.0010 - 125ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0532 - val_loss: 0.0899 - val_mse: 0.0899 - val_mae: 0.2523 - lr: 0.0010 - 110ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0535 - val_loss: 0.0881 - val_mse: 0.0881 - val_mae: 0.2499 - lr: 0.0010 - 100ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0575 - val_loss: 0.0868 - val_mse: 0.0868 - val_mae: 0.2486 - lr: 0.0010 - 112ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0549 - val_loss: 0.0868 - val_mse: 0.0868 - val_mae: 0.2492 - lr: 0.0010 - 106ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00039: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0516 - val_loss: 0.0892 - val_mse: 0.0892 - val_mae: 0.2535 - lr: 0.0010 - 114ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0491 - val_loss: 0.0862 - val_mse: 0.0862 - val_mae: 0.2481 - lr: 1.0000e-04 - 115ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0468 - val_loss: 0.0852 - val_mse: 0.0852 - val_mae: 0.2464 - lr: 1.0000e-04 - 113ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0463 - val_loss: 0.0848 - val_mse: 0.0848 - val_mae: 0.2457 - lr: 1.0000e-04 - 111ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0479 - val_loss: 0.0835 - val_mse: 0.0835 - val_mae: 0.2436 - lr: 1.0000e-04 - 110ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00044: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0482 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2423 - lr: 1.0000e-04 - 104ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0475 - val_loss: 0.0827 - val_mse: 0.0827 - val_mae: 0.2422 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0470 - val_loss: 0.0827 - val_mse: 0.0827 - val_mae: 0.2421 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0462 - val_loss: 0.0827 - val_mse: 0.0827 - val_mae: 0.2422 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0464 - val_loss: 0.0827 - val_mse: 0.0827 - val_mae: 0.2422 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00049: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0457 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2423 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0465 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2424 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0474 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2425 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0475 - val_loss: 0.0829 - val_mse: 0.0829 - val_mae: 0.2426 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0488 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2424 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0481 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2424 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0476 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2424 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0466 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2425 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0032 - mse: 0.0032 - mae: 0.0455 - val_loss: 0.0829 - val_mse: 0.0829 - val_mae: 0.2426 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0509 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2425 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0482 - val_loss: 0.0827 - val_mse: 0.0827 - val_mae: 0.2422 - lr: 1.0000e-05 - 106ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0477 - val_loss: 0.0826 - val_mse: 0.0826 - val_mae: 0.2421 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0478 - val_loss: 0.0825 - val_mse: 0.0825 - val_mae: 0.2420 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0480 - val_loss: 0.0826 - val_mse: 0.0826 - val_mae: 0.2422 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0484 - val_loss: 0.0826 - val_mse: 0.0826 - val_mae: 0.2422 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0478 - val_loss: 0.0827 - val_mse: 0.0827 - val_mae: 0.2423 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0474 - val_loss: 0.0826 - val_mse: 0.0826 - val_mae: 0.2423 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0473 - val_loss: 0.0826 - val_mse: 0.0826 - val_mae: 0.2422 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0466 - val_loss: 0.0827 - val_mse: 0.0827 - val_mae: 0.2423 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0484 - val_loss: 0.0827 - val_mse: 0.0827 - val_mae: 0.2423 - lr: 1.0000e-05 - 106ms/epoch - 6ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0449 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2426 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0480 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2427 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0459 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2425 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0479 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2426 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0471 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2426 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0469 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2426 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0472 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2427 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0465 - val_loss: 0.0828 - val_mse: 0.0828 - val_mae: 0.2427 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0474 - val_loss: 0.0829 - val_mse: 0.0829 - val_mae: 0.2429 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0459 - val_loss: 0.0830 - val_mse: 0.0830 - val_mae: 0.2430 - lr: 1.0000e-05 - 106ms/epoch - 6ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0475 - val_loss: 0.0830 - val_mse: 0.0830 - val_mae: 0.2431 - lr: 1.0000e-05 - 123ms/epoch - 7ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0465 - val_loss: 0.0830 - val_mse: 0.0830 - val_mae: 0.2431 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0468 - val_loss: 0.0831 - val_mse: 0.0831 - val_mae: 0.2433 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0452 - val_loss: 0.0831 - val_mse: 0.0831 - val_mae: 0.2433 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0484 - val_loss: 0.0830 - val_mse: 0.0830 - val_mae: 0.2431 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 84/500

Epoch 00084: val_loss did not improve from 0.08199
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0453 - val_loss: 0.0831 - val_mse: 0.0831 - val_mae: 0.2433 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 00084: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 123.96893050522607 
RMSE:	 11.134133576764116 
MAPE:	 9.602398807260117

EMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 63.919262026708296 
RMSE:	 7.994952284204596 
MAPE:	 6.479287961204322

WMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 24.651058301828286 
RMSE:	 4.9649832126431495 
MAPE:	 3.9308905500983484
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4436.126, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3965.317, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.28 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3736.589, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3598.951, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.68 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.68 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3600.951, Time=0.16 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.335 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1795.475
Date:                Sun, 12 Dec 2021   AIC                           3598.951
Time:                        13:42:31   BIC                           3617.714
Sample:                             0   HQIC                          3606.157
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1983      0.003   -389.581      0.000      -1.204      -1.192
ar.L2         -0.8973      0.006   -139.732      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.649      0.000      -0.410      -0.387
sigma2         5.0573      0.023    215.292      0.000       5.011       5.103
===================================================================================
Ljung-Box (L1) (Q):                  14.41   Jarque-Bera (JB):           2460553.80
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.89
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.08166, saving model to LSTM3.h5
10/10 - 3s - loss: 0.2185 - mse: 0.2185 - mae: 0.3699 - val_loss: 0.0817 - val_mse: 0.0817 - val_mae: 0.2556 - lr: 0.0010 - 3s/epoch - 281ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.08166
10/10 - 0s - loss: 0.0741 - mse: 0.0741 - mae: 0.2322 - val_loss: 0.0922 - val_mse: 0.0922 - val_mae: 0.2767 - lr: 0.0010 - 72ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.08166 to 0.07115, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0418 - mse: 0.0418 - mae: 0.1705 - val_loss: 0.0711 - val_mse: 0.0711 - val_mae: 0.2367 - lr: 0.0010 - 92ms/epoch - 9ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.07115 to 0.06541, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0292 - mse: 0.0292 - mae: 0.1339 - val_loss: 0.0654 - val_mse: 0.0654 - val_mae: 0.2254 - lr: 0.0010 - 94ms/epoch - 9ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.06541
10/10 - 0s - loss: 0.0304 - mse: 0.0304 - mae: 0.1373 - val_loss: 0.0696 - val_mse: 0.0696 - val_mae: 0.2359 - lr: 0.0010 - 77ms/epoch - 8ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.06541
10/10 - 0s - loss: 0.0228 - mse: 0.0228 - mae: 0.1219 - val_loss: 0.0655 - val_mse: 0.0655 - val_mae: 0.2283 - lr: 0.0010 - 75ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.06541 to 0.05387, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0188 - mse: 0.0188 - mae: 0.1095 - val_loss: 0.0539 - val_mse: 0.0539 - val_mae: 0.2021 - lr: 0.0010 - 90ms/epoch - 9ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.05387 to 0.04709, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0178 - mse: 0.0178 - mae: 0.1049 - val_loss: 0.0471 - val_mse: 0.0471 - val_mae: 0.1858 - lr: 0.0010 - 98ms/epoch - 10ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.04709 to 0.04173, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0173 - mse: 0.0173 - mae: 0.1053 - val_loss: 0.0417 - val_mse: 0.0417 - val_mae: 0.1722 - lr: 0.0010 - 97ms/epoch - 10ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.04173 to 0.03636, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0139 - mse: 0.0139 - mae: 0.0929 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1578 - lr: 0.0010 - 99ms/epoch - 10ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.03636 to 0.03305, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0161 - mse: 0.0161 - mae: 0.0994 - val_loss: 0.0330 - val_mse: 0.0330 - val_mae: 0.1487 - lr: 0.0010 - 88ms/epoch - 9ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.03305 to 0.02940, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0131 - mse: 0.0131 - mae: 0.0905 - val_loss: 0.0294 - val_mse: 0.0294 - val_mae: 0.1390 - lr: 0.0010 - 100ms/epoch - 10ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.02940 to 0.02352, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0117 - mse: 0.0117 - mae: 0.0844 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1213 - lr: 0.0010 - 96ms/epoch - 10ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.02352 to 0.02073, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0817 - val_loss: 0.0207 - val_mse: 0.0207 - val_mae: 0.1118 - lr: 0.0010 - 89ms/epoch - 9ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.02073 to 0.01901, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0096 - mse: 0.0096 - mae: 0.0771 - val_loss: 0.0190 - val_mse: 0.0190 - val_mae: 0.1056 - lr: 0.0010 - 94ms/epoch - 9ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.01901 to 0.01814, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0094 - mse: 0.0094 - mae: 0.0754 - val_loss: 0.0181 - val_mse: 0.0181 - val_mae: 0.1021 - lr: 0.0010 - 90ms/epoch - 9ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.01814 to 0.01752, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0094 - mse: 0.0094 - mae: 0.0764 - val_loss: 0.0175 - val_mse: 0.0175 - val_mae: 0.1000 - lr: 0.0010 - 91ms/epoch - 9ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.01752 to 0.01714, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0758 - val_loss: 0.0171 - val_mse: 0.0171 - val_mae: 0.0988 - lr: 0.0010 - 98ms/epoch - 10ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01714
10/10 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0676 - val_loss: 0.0182 - val_mse: 0.0182 - val_mae: 0.1040 - lr: 0.0010 - 79ms/epoch - 8ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.01714 to 0.01697, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0696 - val_loss: 0.0170 - val_mse: 0.0170 - val_mae: 0.0994 - lr: 0.0010 - 91ms/epoch - 9ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0660 - val_loss: 0.0170 - val_mse: 0.0170 - val_mae: 0.1001 - lr: 0.0010 - 80ms/epoch - 8ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0707 - val_loss: 0.0194 - val_mse: 0.0194 - val_mae: 0.1104 - lr: 0.0010 - 77ms/epoch - 8ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0650 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1251 - lr: 0.0010 - 75ms/epoch - 8ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0604 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1279 - lr: 0.0010 - 74ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00025: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0631 - val_loss: 0.0246 - val_mse: 0.0246 - val_mae: 0.1291 - lr: 0.0010 - 70ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0602 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1293 - lr: 1.0000e-04 - 76ms/epoch - 8ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0610 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1299 - lr: 1.0000e-04 - 72ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0641 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1300 - lr: 1.0000e-04 - 75ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0611 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1316 - lr: 1.0000e-04 - 75ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00030: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0593 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1329 - lr: 1.0000e-04 - 83ms/epoch - 8ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0602 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1330 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0612 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1329 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0592 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1329 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0594 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1329 - lr: 1.0000e-05 - 84ms/epoch - 8ms/step
Epoch 35/500

Epoch 00035: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00035: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0636 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1330 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0606 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1330 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0626 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1329 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0623 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1329 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0579 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1328 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0641 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1327 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0571 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1328 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0585 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1328 - lr: 1.0000e-05 - 81ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0601 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1330 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0571 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1331 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0591 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1329 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0640 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1328 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0572 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1327 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0623 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1327 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0599 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1326 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0596 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1325 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0596 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1324 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0596 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1324 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1325 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0600 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1325 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0612 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1325 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0595 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1325 - lr: 1.0000e-05 - 82ms/epoch - 8ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0618 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1325 - lr: 1.0000e-05 - 75ms/epoch - 8ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0629 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1327 - lr: 1.0000e-05 - 83ms/epoch - 8ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0608 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1328 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0596 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1328 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0598 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1330 - lr: 1.0000e-05 - 75ms/epoch - 8ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0635 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1331 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0578 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1332 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0616 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1333 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0619 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1333 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0616 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1331 - lr: 1.0000e-05 - 81ms/epoch - 8ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0583 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1331 - lr: 1.0000e-05 - 81ms/epoch - 8ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0607 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1334 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0578 - val_loss: 0.0261 - val_mse: 0.0261 - val_mae: 0.1336 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.01697
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0595 - val_loss: 0.0261 - val_mse: 0.0261 - val_mae: 0.1337 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 00070: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 123.96893050522607 
RMSE:	 11.134133576764116 
MAPE:	 9.602398807260117

EMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 63.919262026708296 
RMSE:	 7.994952284204596 
MAPE:	 6.479287961204322

WMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 24.651058301828286 
RMSE:	 4.9649832126431495 
MAPE:	 3.9308905500983484

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 156.8635759091866 
RMSE:	 12.524518989134338 
MAPE:	 11.387412907589542
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.31 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4190.464, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3724.371, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.22 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3494.154, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3357.435, Time=0.12 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.44 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.56 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3359.435, Time=0.19 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.943 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1674.717
Date:                Sun, 12 Dec 2021   AIC                           3357.435
Time:                        13:43:43   BIC                           3376.198
Sample:                             0   HQIC                          3364.641
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1955      0.003   -381.246      0.000      -1.202      -1.189
ar.L2         -0.8964      0.007   -135.835      0.000      -0.909      -0.883
ar.L3         -0.3971      0.006    -67.229      0.000      -0.409      -0.385
sigma2         3.7466      0.018    211.623      0.000       3.712       3.781
===================================================================================
Ljung-Box (L1) (Q):                  14.20   Jarque-Bera (JB):           2338363.32
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             3.76
Prob(H) (two-sided):                  0.00   Kurtosis:                       266.93
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.08578, saving model to LSTM3.h5
45/45 - 3s - loss: 0.1392 - mse: 0.1392 - mae: 0.2841 - val_loss: 0.0858 - val_mse: 0.0858 - val_mae: 0.2303 - lr: 0.0010 - 3s/epoch - 77ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.08578 to 0.06798, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0336 - mse: 0.0336 - mae: 0.1463 - val_loss: 0.0680 - val_mse: 0.0680 - val_mae: 0.2133 - lr: 0.0010 - 278ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.06798 to 0.06203, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0172 - mse: 0.0172 - mae: 0.1045 - val_loss: 0.0620 - val_mse: 0.0620 - val_mae: 0.2046 - lr: 0.0010 - 254ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.06203 to 0.05766, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0141 - mse: 0.0141 - mae: 0.0936 - val_loss: 0.0577 - val_mse: 0.0577 - val_mae: 0.1954 - lr: 0.0010 - 265ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.05766 to 0.05452, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0114 - mse: 0.0114 - mae: 0.0851 - val_loss: 0.0545 - val_mse: 0.0545 - val_mae: 0.1874 - lr: 0.0010 - 252ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.05452 to 0.05091, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0098 - mse: 0.0098 - mae: 0.0771 - val_loss: 0.0509 - val_mse: 0.0509 - val_mae: 0.1784 - lr: 0.0010 - 251ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.05091 to 0.05062, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0086 - mse: 0.0086 - mae: 0.0721 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.1721 - lr: 0.0010 - 266ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.05062 to 0.04676, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0703 - val_loss: 0.0468 - val_mse: 0.0468 - val_mae: 0.1681 - lr: 0.0010 - 262ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04676
45/45 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0672 - val_loss: 0.0489 - val_mse: 0.0489 - val_mae: 0.1596 - lr: 0.0010 - 244ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04676
45/45 - 0s - loss: 0.0085 - mse: 0.0085 - mae: 0.0705 - val_loss: 0.0477 - val_mse: 0.0477 - val_mae: 0.1563 - lr: 0.0010 - 258ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.04676 to 0.04290, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0087 - mse: 0.0087 - mae: 0.0714 - val_loss: 0.0429 - val_mse: 0.0429 - val_mae: 0.1535 - lr: 0.0010 - 263ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04290
45/45 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0695 - val_loss: 0.0440 - val_mse: 0.0440 - val_mae: 0.1459 - lr: 0.0010 - 245ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.04290 to 0.04108, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0094 - mse: 0.0094 - mae: 0.0721 - val_loss: 0.0411 - val_mse: 0.0411 - val_mae: 0.1455 - lr: 0.0010 - 257ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.04108 to 0.04037, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0097 - mse: 0.0097 - mae: 0.0758 - val_loss: 0.0404 - val_mse: 0.0404 - val_mae: 0.1409 - lr: 0.0010 - 263ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04037
45/45 - 0s - loss: 0.0100 - mse: 0.0100 - mae: 0.0750 - val_loss: 0.0409 - val_mse: 0.0409 - val_mae: 0.1418 - lr: 0.0010 - 256ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.04037
45/45 - 0s - loss: 0.0121 - mse: 0.0121 - mae: 0.0821 - val_loss: 0.0405 - val_mse: 0.0405 - val_mae: 0.1387 - lr: 0.0010 - 244ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04037
45/45 - 0s - loss: 0.0109 - mse: 0.0109 - mae: 0.0799 - val_loss: 0.0463 - val_mse: 0.0463 - val_mae: 0.1390 - lr: 0.0010 - 233ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04037
45/45 - 0s - loss: 0.0156 - mse: 0.0156 - mae: 0.0954 - val_loss: 0.0453 - val_mse: 0.0453 - val_mae: 0.1371 - lr: 0.0010 - 239ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00019: val_loss did not improve from 0.04037
45/45 - 0s - loss: 0.0146 - mse: 0.0146 - mae: 0.0925 - val_loss: 0.0424 - val_mse: 0.0424 - val_mae: 0.1361 - lr: 0.0010 - 254ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.04037 to 0.03541, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0406 - mse: 0.0406 - mae: 0.1683 - val_loss: 0.0354 - val_mse: 0.0354 - val_mae: 0.1453 - lr: 1.0000e-04 - 261ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.03541 to 0.03531, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0121 - mse: 0.0121 - mae: 0.0925 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1488 - lr: 1.0000e-04 - 252ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0098 - mse: 0.0098 - mae: 0.0822 - val_loss: 0.0356 - val_mse: 0.0356 - val_mae: 0.1487 - lr: 1.0000e-04 - 240ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0092 - mse: 0.0092 - mae: 0.0801 - val_loss: 0.0360 - val_mse: 0.0360 - val_mae: 0.1500 - lr: 1.0000e-04 - 249ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0790 - val_loss: 0.0363 - val_mse: 0.0363 - val_mae: 0.1500 - lr: 1.0000e-04 - 236ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00025: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0085 - mse: 0.0085 - mae: 0.0764 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1507 - lr: 1.0000e-04 - 238ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0708 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1507 - lr: 1.0000e-05 - 247ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0709 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1506 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0718 - val_loss: 0.0369 - val_mse: 0.0369 - val_mae: 0.1506 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0697 - val_loss: 0.0369 - val_mse: 0.0369 - val_mae: 0.1505 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00030: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0697 - val_loss: 0.0369 - val_mse: 0.0369 - val_mae: 0.1505 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0692 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1506 - lr: 1.0000e-05 - 253ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0711 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1505 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0695 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1505 - lr: 1.0000e-05 - 250ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0685 - val_loss: 0.0371 - val_mse: 0.0371 - val_mae: 0.1504 - lr: 1.0000e-05 - 230ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0710 - val_loss: 0.0371 - val_mse: 0.0371 - val_mae: 0.1504 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0680 - val_loss: 0.0372 - val_mse: 0.0372 - val_mae: 0.1504 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0678 - val_loss: 0.0372 - val_mse: 0.0372 - val_mae: 0.1504 - lr: 1.0000e-05 - 243ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0687 - val_loss: 0.0373 - val_mse: 0.0373 - val_mae: 0.1503 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0693 - val_loss: 0.0373 - val_mse: 0.0373 - val_mae: 0.1503 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0717 - val_loss: 0.0374 - val_mse: 0.0374 - val_mae: 0.1502 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0682 - val_loss: 0.0375 - val_mse: 0.0375 - val_mae: 0.1502 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0692 - val_loss: 0.0375 - val_mse: 0.0375 - val_mae: 0.1502 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0705 - val_loss: 0.0376 - val_mse: 0.0376 - val_mae: 0.1500 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0687 - val_loss: 0.0377 - val_mse: 0.0377 - val_mae: 0.1498 - lr: 1.0000e-05 - 249ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0687 - val_loss: 0.0377 - val_mse: 0.0377 - val_mae: 0.1498 - lr: 1.0000e-05 - 247ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0701 - val_loss: 0.0378 - val_mse: 0.0378 - val_mae: 0.1498 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0691 - val_loss: 0.0378 - val_mse: 0.0378 - val_mae: 0.1498 - lr: 1.0000e-05 - 248ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0706 - val_loss: 0.0379 - val_mse: 0.0379 - val_mae: 0.1497 - lr: 1.0000e-05 - 248ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0691 - val_loss: 0.0380 - val_mse: 0.0380 - val_mae: 0.1497 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0682 - val_loss: 0.0381 - val_mse: 0.0381 - val_mae: 0.1496 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0655 - val_loss: 0.0382 - val_mse: 0.0382 - val_mae: 0.1495 - lr: 1.0000e-05 - 243ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0656 - val_loss: 0.0382 - val_mse: 0.0382 - val_mae: 0.1496 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0682 - val_loss: 0.0383 - val_mse: 0.0383 - val_mae: 0.1495 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0658 - val_loss: 0.0384 - val_mse: 0.0384 - val_mae: 0.1494 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0684 - val_loss: 0.0385 - val_mse: 0.0385 - val_mae: 0.1495 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0666 - val_loss: 0.0386 - val_mse: 0.0386 - val_mae: 0.1493 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0674 - val_loss: 0.0387 - val_mse: 0.0387 - val_mae: 0.1493 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0676 - val_loss: 0.0388 - val_mse: 0.0388 - val_mae: 0.1492 - lr: 1.0000e-05 - 231ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0662 - val_loss: 0.0389 - val_mse: 0.0389 - val_mae: 0.1491 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0672 - val_loss: 0.0390 - val_mse: 0.0390 - val_mae: 0.1492 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0658 - val_loss: 0.0390 - val_mse: 0.0390 - val_mae: 0.1492 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0653 - val_loss: 0.0392 - val_mse: 0.0392 - val_mae: 0.1492 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0642 - val_loss: 0.0393 - val_mse: 0.0393 - val_mae: 0.1492 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0645 - val_loss: 0.0393 - val_mse: 0.0393 - val_mae: 0.1493 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0626 - val_loss: 0.0395 - val_mse: 0.0395 - val_mae: 0.1492 - lr: 1.0000e-05 - 251ms/epoch - 6ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0660 - val_loss: 0.0396 - val_mse: 0.0396 - val_mae: 0.1492 - lr: 1.0000e-05 - 252ms/epoch - 6ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0642 - val_loss: 0.0397 - val_mse: 0.0397 - val_mae: 0.1491 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0640 - val_loss: 0.0398 - val_mse: 0.0398 - val_mae: 0.1491 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0629 - val_loss: 0.0400 - val_mse: 0.0400 - val_mae: 0.1491 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0667 - val_loss: 0.0401 - val_mse: 0.0401 - val_mae: 0.1492 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.03531
45/45 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0610 - val_loss: 0.0402 - val_mse: 0.0402 - val_mae: 0.1492 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 00071: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 123.96893050522607 
RMSE:	 11.134133576764116 
MAPE:	 9.602398807260117

EMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 63.919262026708296 
RMSE:	 7.994952284204596 
MAPE:	 6.479287961204322

WMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 24.651058301828286 
RMSE:	 4.9649832126431495 
MAPE:	 3.9308905500983484

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 156.8635759091866 
RMSE:	 12.524518989134338 
MAPE:	 11.387412907589542

KAMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 59.19746610115158 
RMSE:	 7.69398895899595 
MAPE:	 6.776737847872761
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.32 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4212.289, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3747.746, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.18 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3523.401, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3387.759, Time=0.07 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.90 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.61 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3389.758, Time=0.15 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.352 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1689.879
Date:                Sun, 12 Dec 2021   AIC                           3387.759
Time:                        13:45:17   BIC                           3406.522
Sample:                             0   HQIC                          3394.964
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1878      0.003   -345.315      0.000      -1.195      -1.181
ar.L2         -0.8876      0.007   -121.809      0.000      -0.902      -0.873
ar.L3         -0.3957      0.007    -60.127      0.000      -0.409      -0.383
sigma2         3.8904      0.020    193.404      0.000       3.851       3.930
===================================================================================
Ljung-Box (L1) (Q):                  13.21   Jarque-Bera (JB):           1659080.01
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.08   Skew:                             3.28
Prob(H) (two-sided):                  0.00   Kurtosis:                       225.31
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.36509, saving model to LSTM3.h5
58/58 - 3s - loss: 0.1032 - mse: 0.1032 - mae: 0.2314 - val_loss: 0.3651 - val_mse: 0.3651 - val_mae: 0.5743 - lr: 0.0010 - 3s/epoch - 52ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.36509
58/58 - 0s - loss: 0.0213 - mse: 0.0213 - mae: 0.1163 - val_loss: 0.3714 - val_mse: 0.3714 - val_mae: 0.5833 - lr: 0.0010 - 301ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.36509 to 0.26686, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0166 - mse: 0.0166 - mae: 0.1008 - val_loss: 0.2669 - val_mse: 0.2669 - val_mae: 0.4911 - lr: 0.0010 - 327ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.26686
58/58 - 0s - loss: 0.0113 - mse: 0.0113 - mae: 0.0836 - val_loss: 0.2773 - val_mse: 0.2773 - val_mae: 0.5038 - lr: 0.0010 - 304ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.26686 to 0.18693, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0817 - val_loss: 0.1869 - val_mse: 0.1869 - val_mae: 0.4054 - lr: 0.0010 - 329ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.18693
58/58 - 0s - loss: 0.0091 - mse: 0.0091 - mae: 0.0756 - val_loss: 0.2327 - val_mse: 0.2327 - val_mae: 0.4609 - lr: 0.0010 - 297ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.18693 to 0.13637, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0756 - val_loss: 0.1364 - val_mse: 0.1364 - val_mae: 0.3435 - lr: 0.0010 - 339ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.13637
58/58 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0660 - val_loss: 0.1913 - val_mse: 0.1913 - val_mae: 0.4148 - lr: 0.0010 - 300ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.13637 to 0.08219, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0089 - mse: 0.0089 - mae: 0.0730 - val_loss: 0.0822 - val_mse: 0.0822 - val_mae: 0.2581 - lr: 0.0010 - 318ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.08219
58/58 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0647 - val_loss: 0.1769 - val_mse: 0.1769 - val_mae: 0.3982 - lr: 0.0010 - 308ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.08219 to 0.05422, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0801 - val_loss: 0.0542 - val_mse: 0.0542 - val_mae: 0.2005 - lr: 0.0010 - 316ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05422
58/58 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0609 - val_loss: 0.1559 - val_mse: 0.1559 - val_mae: 0.3738 - lr: 0.0010 - 283ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.05422 to 0.03917, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0108 - mse: 0.0108 - mae: 0.0783 - val_loss: 0.0392 - val_mse: 0.0392 - val_mae: 0.1653 - lr: 0.0010 - 324ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03917
58/58 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0625 - val_loss: 0.1523 - val_mse: 0.1523 - val_mae: 0.3712 - lr: 0.0010 - 306ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.03917 to 0.01711, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0131 - mse: 0.0131 - mae: 0.0872 - val_loss: 0.0171 - val_mse: 0.0171 - val_mae: 0.0982 - lr: 0.0010 - 308ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.01711
58/58 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0649 - val_loss: 0.1457 - val_mse: 0.1457 - val_mae: 0.3636 - lr: 0.0010 - 311ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.01711 to 0.01155, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0149 - mse: 0.0149 - mae: 0.0910 - val_loss: 0.0115 - val_mse: 0.0115 - val_mae: 0.0818 - lr: 0.0010 - 321ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0658 - val_loss: 0.0945 - val_mse: 0.0945 - val_mae: 0.2906 - lr: 0.0010 - 303ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0136 - mse: 0.0136 - mae: 0.0880 - val_loss: 0.0161 - val_mse: 0.0161 - val_mae: 0.0962 - lr: 0.0010 - 311ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0654 - val_loss: 0.0877 - val_mse: 0.0877 - val_mae: 0.2806 - lr: 0.0010 - 298ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0121 - mse: 0.0121 - mae: 0.0836 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1198 - lr: 0.0010 - 308ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00022: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0698 - val_loss: 0.0542 - val_mse: 0.0542 - val_mae: 0.2153 - lr: 0.0010 - 310ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0289 - mse: 0.0289 - mae: 0.1435 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1435 - lr: 1.0000e-04 - 306ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0098 - mse: 0.0098 - mae: 0.0837 - val_loss: 0.0222 - val_mse: 0.0222 - val_mae: 0.1266 - lr: 1.0000e-04 - 299ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0735 - val_loss: 0.0201 - val_mse: 0.0201 - val_mae: 0.1178 - lr: 1.0000e-04 - 299ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0704 - val_loss: 0.0189 - val_mse: 0.0189 - val_mae: 0.1127 - lr: 1.0000e-04 - 297ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00027: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0707 - val_loss: 0.0192 - val_mse: 0.0192 - val_mae: 0.1131 - lr: 1.0000e-04 - 293ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0671 - val_loss: 0.0192 - val_mse: 0.0192 - val_mae: 0.1129 - lr: 1.0000e-05 - 309ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0664 - val_loss: 0.0190 - val_mse: 0.0190 - val_mae: 0.1125 - lr: 1.0000e-05 - 313ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0654 - val_loss: 0.0189 - val_mse: 0.0189 - val_mae: 0.1120 - lr: 1.0000e-05 - 300ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0664 - val_loss: 0.0187 - val_mse: 0.0187 - val_mae: 0.1112 - lr: 1.0000e-05 - 302ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00032: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0647 - val_loss: 0.0187 - val_mse: 0.0187 - val_mae: 0.1111 - lr: 1.0000e-05 - 303ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0622 - val_loss: 0.0187 - val_mse: 0.0187 - val_mae: 0.1109 - lr: 1.0000e-05 - 302ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0616 - val_loss: 0.0187 - val_mse: 0.0187 - val_mae: 0.1109 - lr: 1.0000e-05 - 290ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0661 - val_loss: 0.0187 - val_mse: 0.0187 - val_mae: 0.1109 - lr: 1.0000e-05 - 307ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0634 - val_loss: 0.0187 - val_mse: 0.0187 - val_mae: 0.1108 - lr: 1.0000e-05 - 308ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0629 - val_loss: 0.0187 - val_mse: 0.0187 - val_mae: 0.1109 - lr: 1.0000e-05 - 298ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0630 - val_loss: 0.0188 - val_mse: 0.0188 - val_mae: 0.1110 - lr: 1.0000e-05 - 292ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0648 - val_loss: 0.0189 - val_mse: 0.0189 - val_mae: 0.1113 - lr: 1.0000e-05 - 317ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0641 - val_loss: 0.0189 - val_mse: 0.0189 - val_mae: 0.1116 - lr: 1.0000e-05 - 291ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0661 - val_loss: 0.0189 - val_mse: 0.0189 - val_mae: 0.1113 - lr: 1.0000e-05 - 288ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0660 - val_loss: 0.0189 - val_mse: 0.0189 - val_mae: 0.1112 - lr: 1.0000e-05 - 304ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0638 - val_loss: 0.0190 - val_mse: 0.0190 - val_mae: 0.1116 - lr: 1.0000e-05 - 299ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0597 - val_loss: 0.0191 - val_mse: 0.0191 - val_mae: 0.1118 - lr: 1.0000e-05 - 294ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0644 - val_loss: 0.0190 - val_mse: 0.0190 - val_mae: 0.1115 - lr: 1.0000e-05 - 307ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0597 - val_loss: 0.0190 - val_mse: 0.0190 - val_mae: 0.1115 - lr: 1.0000e-05 - 299ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0607 - val_loss: 0.0191 - val_mse: 0.0191 - val_mae: 0.1115 - lr: 1.0000e-05 - 301ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0617 - val_loss: 0.0192 - val_mse: 0.0192 - val_mae: 0.1120 - lr: 1.0000e-05 - 303ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0627 - val_loss: 0.0194 - val_mse: 0.0194 - val_mae: 0.1126 - lr: 1.0000e-05 - 319ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0607 - val_loss: 0.0194 - val_mse: 0.0194 - val_mae: 0.1126 - lr: 1.0000e-05 - 302ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0603 - val_loss: 0.0194 - val_mse: 0.0194 - val_mae: 0.1126 - lr: 1.0000e-05 - 296ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0599 - val_loss: 0.0195 - val_mse: 0.0195 - val_mae: 0.1129 - lr: 1.0000e-05 - 306ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0583 - val_loss: 0.0197 - val_mse: 0.0197 - val_mae: 0.1136 - lr: 1.0000e-05 - 293ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0607 - val_loss: 0.0197 - val_mse: 0.0197 - val_mae: 0.1135 - lr: 1.0000e-05 - 305ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0591 - val_loss: 0.0198 - val_mse: 0.0198 - val_mae: 0.1137 - lr: 1.0000e-05 - 301ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0572 - val_loss: 0.0199 - val_mse: 0.0199 - val_mae: 0.1141 - lr: 1.0000e-05 - 305ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0565 - val_loss: 0.0200 - val_mse: 0.0200 - val_mae: 0.1145 - lr: 1.0000e-05 - 297ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0613 - val_loss: 0.0201 - val_mse: 0.0201 - val_mae: 0.1146 - lr: 1.0000e-05 - 309ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0621 - val_loss: 0.0202 - val_mse: 0.0202 - val_mae: 0.1149 - lr: 1.0000e-05 - 302ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0582 - val_loss: 0.0203 - val_mse: 0.0203 - val_mae: 0.1155 - lr: 1.0000e-05 - 296ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0597 - val_loss: 0.0205 - val_mse: 0.0205 - val_mae: 0.1161 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0594 - val_loss: 0.0206 - val_mse: 0.0206 - val_mae: 0.1162 - lr: 1.0000e-05 - 303ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0579 - val_loss: 0.0209 - val_mse: 0.0209 - val_mae: 0.1171 - lr: 1.0000e-05 - 299ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0594 - val_loss: 0.0211 - val_mse: 0.0211 - val_mae: 0.1179 - lr: 1.0000e-05 - 308ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0590 - val_loss: 0.0212 - val_mse: 0.0212 - val_mae: 0.1182 - lr: 1.0000e-05 - 303ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0596 - val_loss: 0.0213 - val_mse: 0.0213 - val_mae: 0.1183 - lr: 1.0000e-05 - 294ms/epoch - 5ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.01155
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0574 - val_loss: 0.0215 - val_mse: 0.0215 - val_mae: 0.1191 - lr: 1.0000e-05 - 296ms/epoch - 5ms/step
Epoch 00067: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 123.96893050522607 
RMSE:	 11.134133576764116 
MAPE:	 9.602398807260117

EMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 63.919262026708296 
RMSE:	 7.994952284204596 
MAPE:	 6.479287961204322

WMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 24.651058301828286 
RMSE:	 4.9649832126431495 
MAPE:	 3.9308905500983484

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 156.8635759091866 
RMSE:	 12.524518989134338 
MAPE:	 11.387412907589542

KAMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 59.19746610115158 
RMSE:	 7.69398895899595 
MAPE:	 6.776737847872761

MIDPOINT
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 46.490023595118274 
RMSE:	 6.818359303756166 
MAPE:	 5.538801606657957
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.32 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4414.515, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3944.062, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.25 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3715.173, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3577.471, Time=0.06 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.02 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.41 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3579.471, Time=0.14 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.316 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1784.736
Date:                Sun, 12 Dec 2021   AIC                           3577.471
Time:                        13:47:01   BIC                           3596.235
Sample:                             0   HQIC                          3584.677
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.844      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.861      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.862      0.000      -0.410      -0.387
sigma2         4.9242      0.023    215.469      0.000       4.879       4.969
===================================================================================
Ljung-Box (L1) (Q):                  14.55   Jarque-Bera (JB):           2468024.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       274.15
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.78033, saving model to LSTM3.h5
43/43 - 3s - loss: 0.1572 - mse: 0.1572 - mae: 0.3172 - val_loss: 0.7803 - val_mse: 0.7803 - val_mae: 0.8584 - lr: 0.0010 - 3s/epoch - 80ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.78033 to 0.31463, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0652 - mse: 0.0652 - mae: 0.2098 - val_loss: 0.3146 - val_mse: 0.3146 - val_mae: 0.5364 - lr: 0.0010 - 265ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.31463 to 0.17210, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0324 - mse: 0.0324 - mae: 0.1441 - val_loss: 0.1721 - val_mse: 0.1721 - val_mae: 0.3885 - lr: 0.0010 - 251ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.17210 to 0.13935, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0208 - mse: 0.0208 - mae: 0.1148 - val_loss: 0.1394 - val_mse: 0.1394 - val_mae: 0.3462 - lr: 0.0010 - 249ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.13935 to 0.12467, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0178 - mse: 0.0178 - mae: 0.1064 - val_loss: 0.1247 - val_mse: 0.1247 - val_mae: 0.3259 - lr: 0.0010 - 245ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.12467 to 0.12418, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0159 - mse: 0.0159 - mae: 0.1017 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3253 - lr: 0.0010 - 261ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.12418 to 0.11508, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0136 - mse: 0.0136 - mae: 0.0925 - val_loss: 0.1151 - val_mse: 0.1151 - val_mae: 0.3120 - lr: 0.0010 - 281ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.11508 to 0.10550, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0140 - mse: 0.0140 - mae: 0.0952 - val_loss: 0.1055 - val_mse: 0.1055 - val_mae: 0.2971 - lr: 0.0010 - 250ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.10550 to 0.10018, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0131 - mse: 0.0131 - mae: 0.0908 - val_loss: 0.1002 - val_mse: 0.1002 - val_mae: 0.2888 - lr: 0.0010 - 248ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.10018 to 0.09417, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0114 - mse: 0.0114 - mae: 0.0851 - val_loss: 0.0942 - val_mse: 0.0942 - val_mae: 0.2790 - lr: 0.0010 - 270ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.09417
43/43 - 0s - loss: 0.0121 - mse: 0.0121 - mae: 0.0872 - val_loss: 0.0966 - val_mse: 0.0966 - val_mae: 0.2830 - lr: 0.0010 - 232ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.09417
43/43 - 0s - loss: 0.0128 - mse: 0.0128 - mae: 0.0914 - val_loss: 0.1021 - val_mse: 0.1021 - val_mae: 0.2916 - lr: 0.0010 - 228ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.09417
43/43 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0891 - val_loss: 0.1058 - val_mse: 0.1058 - val_mae: 0.2974 - lr: 0.0010 - 232ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.09417
43/43 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0877 - val_loss: 0.0944 - val_mse: 0.0944 - val_mae: 0.2785 - lr: 0.0010 - 241ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.09417 to 0.08504, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0833 - val_loss: 0.0850 - val_mse: 0.0850 - val_mae: 0.2623 - lr: 0.0010 - 245ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.08504
43/43 - 0s - loss: 0.0101 - mse: 0.0101 - mae: 0.0820 - val_loss: 0.0960 - val_mse: 0.0960 - val_mae: 0.2798 - lr: 0.0010 - 223ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.08504
43/43 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0851 - val_loss: 0.1018 - val_mse: 0.1018 - val_mae: 0.2887 - lr: 0.0010 - 229ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.08504
43/43 - 0s - loss: 0.0107 - mse: 0.0107 - mae: 0.0831 - val_loss: 0.1003 - val_mse: 0.1003 - val_mae: 0.2854 - lr: 0.0010 - 245ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.08504
43/43 - 0s - loss: 0.0104 - mse: 0.0104 - mae: 0.0820 - val_loss: 0.0957 - val_mse: 0.0957 - val_mae: 0.2777 - lr: 0.0010 - 235ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.08504 to 0.07169, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0099 - mse: 0.0099 - mae: 0.0802 - val_loss: 0.0717 - val_mse: 0.0717 - val_mae: 0.2358 - lr: 0.0010 - 256ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.07169
43/43 - 0s - loss: 0.0098 - mse: 0.0098 - mae: 0.0801 - val_loss: 0.0895 - val_mse: 0.0895 - val_mae: 0.2674 - lr: 0.0010 - 224ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.07169
43/43 - 0s - loss: 0.0101 - mse: 0.0101 - mae: 0.0811 - val_loss: 0.0840 - val_mse: 0.0840 - val_mae: 0.2573 - lr: 0.0010 - 237ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.07169
43/43 - 0s - loss: 0.0092 - mse: 0.0092 - mae: 0.0759 - val_loss: 0.0847 - val_mse: 0.0847 - val_mae: 0.2584 - lr: 0.0010 - 229ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.07169
43/43 - 0s - loss: 0.0099 - mse: 0.0099 - mae: 0.0795 - val_loss: 0.0867 - val_mse: 0.0867 - val_mae: 0.2619 - lr: 0.0010 - 234ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00025: val_loss did not improve from 0.07169
43/43 - 0s - loss: 0.0095 - mse: 0.0095 - mae: 0.0783 - val_loss: 0.0803 - val_mse: 0.0803 - val_mae: 0.2507 - lr: 0.0010 - 238ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss improved from 0.07169 to 0.06618, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0143 - mse: 0.0143 - mae: 0.0968 - val_loss: 0.0662 - val_mse: 0.0662 - val_mae: 0.2247 - lr: 1.0000e-04 - 256ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss improved from 0.06618 to 0.06242, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0630 - val_loss: 0.0624 - val_mse: 0.0624 - val_mae: 0.2174 - lr: 1.0000e-04 - 256ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss improved from 0.06242 to 0.06165, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0563 - val_loss: 0.0617 - val_mse: 0.0617 - val_mae: 0.2158 - lr: 1.0000e-04 - 256ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0551 - val_loss: 0.0620 - val_mse: 0.0620 - val_mae: 0.2163 - lr: 1.0000e-04 - 228ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0545 - val_loss: 0.0622 - val_mse: 0.0622 - val_mae: 0.2166 - lr: 1.0000e-04 - 240ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0557 - val_loss: 0.0626 - val_mse: 0.0626 - val_mae: 0.2172 - lr: 1.0000e-04 - 232ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0522 - val_loss: 0.0637 - val_mse: 0.0637 - val_mae: 0.2193 - lr: 1.0000e-04 - 228ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00033: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0542 - val_loss: 0.0641 - val_mse: 0.0641 - val_mae: 0.2201 - lr: 1.0000e-04 - 236ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0531 - val_loss: 0.0642 - val_mse: 0.0642 - val_mae: 0.2202 - lr: 1.0000e-05 - 238ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0528 - val_loss: 0.0643 - val_mse: 0.0643 - val_mae: 0.2204 - lr: 1.0000e-05 - 243ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0518 - val_loss: 0.0644 - val_mse: 0.0644 - val_mae: 0.2205 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0544 - val_loss: 0.0643 - val_mse: 0.0643 - val_mae: 0.2204 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00038: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0524 - val_loss: 0.0642 - val_mse: 0.0642 - val_mae: 0.2203 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0531 - val_loss: 0.0644 - val_mse: 0.0644 - val_mae: 0.2205 - lr: 1.0000e-05 - 246ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0504 - val_loss: 0.0645 - val_mse: 0.0645 - val_mae: 0.2207 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0507 - val_loss: 0.0645 - val_mse: 0.0645 - val_mae: 0.2207 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0542 - val_loss: 0.0644 - val_mse: 0.0644 - val_mae: 0.2205 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0508 - val_loss: 0.0643 - val_mse: 0.0643 - val_mae: 0.2204 - lr: 1.0000e-05 - 242ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.0641 - val_mse: 0.0641 - val_mae: 0.2200 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0546 - val_loss: 0.0642 - val_mse: 0.0642 - val_mae: 0.2201 - lr: 1.0000e-05 - 233ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0502 - val_loss: 0.0641 - val_mse: 0.0641 - val_mae: 0.2199 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0503 - val_loss: 0.0640 - val_mse: 0.0640 - val_mae: 0.2198 - lr: 1.0000e-05 - 244ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0518 - val_loss: 0.0640 - val_mse: 0.0640 - val_mae: 0.2197 - lr: 1.0000e-05 - 243ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0537 - val_loss: 0.0639 - val_mse: 0.0639 - val_mae: 0.2194 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.0637 - val_mse: 0.0637 - val_mae: 0.2191 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0532 - val_loss: 0.0637 - val_mse: 0.0637 - val_mae: 0.2190 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0513 - val_loss: 0.0638 - val_mse: 0.0638 - val_mae: 0.2192 - lr: 1.0000e-05 - 244ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0500 - val_loss: 0.0641 - val_mse: 0.0641 - val_mae: 0.2199 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0505 - val_loss: 0.0644 - val_mse: 0.0644 - val_mae: 0.2204 - lr: 1.0000e-05 - 231ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0525 - val_loss: 0.0645 - val_mse: 0.0645 - val_mae: 0.2205 - lr: 1.0000e-05 - 241ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.0646 - val_mse: 0.0646 - val_mae: 0.2207 - lr: 1.0000e-05 - 245ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0527 - val_loss: 0.0645 - val_mse: 0.0645 - val_mae: 0.2206 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0498 - val_loss: 0.0646 - val_mse: 0.0646 - val_mae: 0.2208 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0529 - val_loss: 0.0650 - val_mse: 0.0650 - val_mae: 0.2215 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0539 - val_loss: 0.0652 - val_mse: 0.0652 - val_mae: 0.2218 - lr: 1.0000e-05 - 239ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0524 - val_loss: 0.0650 - val_mse: 0.0650 - val_mae: 0.2214 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.0650 - val_mse: 0.0650 - val_mae: 0.2213 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0535 - val_loss: 0.0652 - val_mse: 0.0652 - val_mae: 0.2217 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0508 - val_loss: 0.0650 - val_mse: 0.0650 - val_mae: 0.2215 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0517 - val_loss: 0.0650 - val_mse: 0.0650 - val_mae: 0.2215 - lr: 1.0000e-05 - 240ms/epoch - 6ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0496 - val_loss: 0.0650 - val_mse: 0.0650 - val_mae: 0.2214 - lr: 1.0000e-05 - 235ms/epoch - 5ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0528 - val_loss: 0.0650 - val_mse: 0.0650 - val_mae: 0.2214 - lr: 1.0000e-05 - 245ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0498 - val_loss: 0.0651 - val_mse: 0.0651 - val_mae: 0.2217 - lr: 1.0000e-05 - 245ms/epoch - 6ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.0649 - val_mse: 0.0649 - val_mae: 0.2211 - lr: 1.0000e-05 - 243ms/epoch - 6ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0489 - val_loss: 0.0648 - val_mse: 0.0648 - val_mae: 0.2210 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0504 - val_loss: 0.0648 - val_mse: 0.0648 - val_mae: 0.2209 - lr: 1.0000e-05 - 243ms/epoch - 6ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0539 - val_loss: 0.0647 - val_mse: 0.0647 - val_mae: 0.2207 - lr: 1.0000e-05 - 240ms/epoch - 6ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0509 - val_loss: 0.0649 - val_mse: 0.0649 - val_mae: 0.2212 - lr: 1.0000e-05 - 238ms/epoch - 6ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0500 - val_loss: 0.0648 - val_mse: 0.0648 - val_mae: 0.2208 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0506 - val_loss: 0.0645 - val_mse: 0.0645 - val_mae: 0.2202 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0508 - val_loss: 0.0647 - val_mse: 0.0647 - val_mae: 0.2206 - lr: 1.0000e-05 - 237ms/epoch - 6ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.0648 - val_mse: 0.0648 - val_mae: 0.2208 - lr: 1.0000e-05 - 241ms/epoch - 6ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.06165
43/43 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0502 - val_loss: 0.0647 - val_mse: 0.0647 - val_mae: 0.2207 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 00078: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 123.96893050522607 
RMSE:	 11.134133576764116 
MAPE:	 9.602398807260117

EMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 63.919262026708296 
RMSE:	 7.994952284204596 
MAPE:	 6.479287961204322

WMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 24.651058301828286 
RMSE:	 4.9649832126431495 
MAPE:	 3.9308905500983484

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 156.8635759091866 
RMSE:	 12.524518989134338 
MAPE:	 11.387412907589542

KAMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 59.19746610115158 
RMSE:	 7.69398895899595 
MAPE:	 6.776737847872761

MIDPOINT
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 46.490023595118274 
RMSE:	 6.818359303756166 
MAPE:	 5.538801606657957

T3
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	51.12% Accuracy
MSE:	 57.75776139981352 
RMSE:	 7.59985272224492 
MAPE:	 6.172107202063374
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.40 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4352.703, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3889.412, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.21 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3689.930, Time=0.04 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3574.245, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.37 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.59 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3576.245, Time=0.21 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.985 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1783.123
Date:                Sun, 12 Dec 2021   AIC                           3574.245
Time:                        13:48:39   BIC                           3593.008
Sample:                             0   HQIC                          3581.451
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1480      0.004   -302.430      0.000      -1.155      -1.141
ar.L2         -0.8300      0.008    -99.682      0.000      -0.846      -0.814
ar.L3         -0.3687      0.007    -50.527      0.000      -0.383      -0.354
sigma2         4.9055      0.028    175.970      0.000       4.851       4.960
===================================================================================
Ljung-Box (L1) (Q):                  11.61   Jarque-Bera (JB):           1261976.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.16   Skew:                             2.52
Prob(H) (two-sided):                  0.00   Kurtosis:                       196.90
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.07907, saving model to LSTM3.h5
90/90 - 3s - loss: 0.0502 - mse: 0.0502 - mae: 0.1781 - val_loss: 0.0791 - val_mse: 0.0791 - val_mae: 0.2511 - lr: 0.0010 - 3s/epoch - 35ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.07907 to 0.05916, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0170 - mse: 0.0170 - mae: 0.1027 - val_loss: 0.0592 - val_mse: 0.0592 - val_mae: 0.2091 - lr: 0.0010 - 478ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05916
90/90 - 0s - loss: 0.0210 - mse: 0.0210 - mae: 0.1174 - val_loss: 0.0799 - val_mse: 0.0799 - val_mae: 0.2511 - lr: 0.0010 - 448ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.05916 to 0.04150, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0451 - mse: 0.0451 - mae: 0.1690 - val_loss: 0.0415 - val_mse: 0.0415 - val_mae: 0.1713 - lr: 0.0010 - 473ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04150
90/90 - 0s - loss: 0.0349 - mse: 0.0349 - mae: 0.1438 - val_loss: 0.0732 - val_mse: 0.0732 - val_mae: 0.2349 - lr: 0.0010 - 442ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.04150 to 0.02530, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0180 - mse: 0.0180 - mae: 0.0969 - val_loss: 0.0253 - val_mse: 0.0253 - val_mae: 0.1290 - lr: 0.0010 - 466ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.02530
90/90 - 0s - loss: 0.0102 - mse: 0.0102 - mae: 0.0747 - val_loss: 0.0759 - val_mse: 0.0759 - val_mae: 0.2374 - lr: 0.0010 - 449ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.02530 to 0.02285, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0125 - mse: 0.0125 - mae: 0.0833 - val_loss: 0.0229 - val_mse: 0.0229 - val_mae: 0.1208 - lr: 0.0010 - 481ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.02285
90/90 - 0s - loss: 0.0099 - mse: 0.0099 - mae: 0.0738 - val_loss: 0.0928 - val_mse: 0.0928 - val_mae: 0.2619 - lr: 0.0010 - 446ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.02285 to 0.02038, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0113 - mse: 0.0113 - mae: 0.0775 - val_loss: 0.0204 - val_mse: 0.0204 - val_mae: 0.1136 - lr: 0.0010 - 482ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.02038
90/90 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0707 - val_loss: 0.0728 - val_mse: 0.0728 - val_mae: 0.2291 - lr: 0.0010 - 449ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.02038 to 0.01891, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0109 - mse: 0.0109 - mae: 0.0779 - val_loss: 0.0189 - val_mse: 0.0189 - val_mae: 0.1109 - lr: 0.0010 - 477ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01891
90/90 - 0s - loss: 0.0089 - mse: 0.0089 - mae: 0.0713 - val_loss: 0.0716 - val_mse: 0.0716 - val_mae: 0.2254 - lr: 0.0010 - 456ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.01891 to 0.01859, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0098 - mse: 0.0098 - mae: 0.0735 - val_loss: 0.0186 - val_mse: 0.0186 - val_mae: 0.1106 - lr: 0.0010 - 485ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01859
90/90 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0681 - val_loss: 0.0556 - val_mse: 0.0556 - val_mae: 0.1956 - lr: 0.0010 - 439ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.01859 to 0.01584, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0087 - mse: 0.0087 - mae: 0.0700 - val_loss: 0.0158 - val_mse: 0.0158 - val_mae: 0.1005 - lr: 0.0010 - 471ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0659 - val_loss: 0.0572 - val_mse: 0.0572 - val_mae: 0.1978 - lr: 0.0010 - 446ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0708 - val_loss: 0.0201 - val_mse: 0.0201 - val_mae: 0.1110 - lr: 0.0010 - 452ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0625 - val_loss: 0.0532 - val_mse: 0.0532 - val_mae: 0.1895 - lr: 0.0010 - 449ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0087 - mse: 0.0087 - mae: 0.0700 - val_loss: 0.0215 - val_mse: 0.0215 - val_mae: 0.1119 - lr: 0.0010 - 435ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00021: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0683 - val_loss: 0.0607 - val_mse: 0.0607 - val_mae: 0.2059 - lr: 0.0010 - 462ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0192 - mse: 0.0192 - mae: 0.1141 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1407 - lr: 1.0000e-04 - 444ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0650 - val_loss: 0.0307 - val_mse: 0.0307 - val_mae: 0.1348 - lr: 1.0000e-04 - 459ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0606 - val_loss: 0.0308 - val_mse: 0.0308 - val_mae: 0.1336 - lr: 1.0000e-04 - 446ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0605 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1341 - lr: 1.0000e-04 - 472ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00026: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0596 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1346 - lr: 1.0000e-04 - 449ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0577 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1333 - lr: 1.0000e-05 - 467ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0533 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1326 - lr: 1.0000e-05 - 439ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0556 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1319 - lr: 1.0000e-05 - 450ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0543 - val_loss: 0.0307 - val_mse: 0.0307 - val_mae: 0.1314 - lr: 1.0000e-05 - 463ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00031: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0531 - val_loss: 0.0306 - val_mse: 0.0306 - val_mae: 0.1311 - lr: 1.0000e-05 - 447ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0520 - val_loss: 0.0306 - val_mse: 0.0306 - val_mae: 0.1311 - lr: 1.0000e-05 - 455ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0520 - val_loss: 0.0307 - val_mse: 0.0307 - val_mae: 0.1313 - lr: 1.0000e-05 - 432ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0501 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1317 - lr: 1.0000e-05 - 461ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0540 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1318 - lr: 1.0000e-05 - 444ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0559 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1318 - lr: 1.0000e-05 - 439ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0535 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1317 - lr: 1.0000e-05 - 460ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0519 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1321 - lr: 1.0000e-05 - 463ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0524 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1325 - lr: 1.0000e-05 - 442ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0536 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1328 - lr: 1.0000e-05 - 455ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0522 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1326 - lr: 1.0000e-05 - 458ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0536 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1334 - lr: 1.0000e-05 - 447ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0519 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1338 - lr: 1.0000e-05 - 470ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0528 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1337 - lr: 1.0000e-05 - 434ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0514 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1345 - lr: 1.0000e-05 - 458ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0529 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1348 - lr: 1.0000e-05 - 449ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0526 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1360 - lr: 1.0000e-05 - 453ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0532 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1360 - lr: 1.0000e-05 - 451ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0517 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1368 - lr: 1.0000e-05 - 452ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0501 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1371 - lr: 1.0000e-05 - 444ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0519 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1381 - lr: 1.0000e-05 - 453ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0518 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1381 - lr: 1.0000e-05 - 462ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0518 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1385 - lr: 1.0000e-05 - 450ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0536 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1382 - lr: 1.0000e-05 - 466ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0509 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1385 - lr: 1.0000e-05 - 433ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0507 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1376 - lr: 1.0000e-05 - 452ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0504 - val_loss: 0.0345 - val_mse: 0.0345 - val_mae: 0.1385 - lr: 1.0000e-05 - 442ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0529 - val_loss: 0.0350 - val_mse: 0.0350 - val_mae: 0.1398 - lr: 1.0000e-05 - 450ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0503 - val_loss: 0.0355 - val_mse: 0.0355 - val_mae: 0.1408 - lr: 1.0000e-05 - 432ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0520 - val_loss: 0.0356 - val_mse: 0.0356 - val_mae: 0.1410 - lr: 1.0000e-05 - 434ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0515 - val_loss: 0.0355 - val_mse: 0.0355 - val_mae: 0.1408 - lr: 1.0000e-05 - 469ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0521 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1400 - lr: 1.0000e-05 - 466ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0501 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1400 - lr: 1.0000e-05 - 459ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0505 - val_loss: 0.0357 - val_mse: 0.0357 - val_mae: 0.1410 - lr: 1.0000e-05 - 444ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0504 - val_loss: 0.0363 - val_mse: 0.0363 - val_mae: 0.1423 - lr: 1.0000e-05 - 451ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.01584
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0527 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1431 - lr: 1.0000e-05 - 445ms/epoch - 5ms/step
Epoch 00066: early stopping

SMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 123.96893050522607 
RMSE:	 11.134133576764116 
MAPE:	 9.602398807260117

EMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 63.919262026708296 
RMSE:	 7.994952284204596 
MAPE:	 6.479287961204322

WMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 24.651058301828286 
RMSE:	 4.9649832126431495 
MAPE:	 3.9308905500983484

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 156.8635759091866 
RMSE:	 12.524518989134338 
MAPE:	 11.387412907589542

KAMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 59.19746610115158 
RMSE:	 7.69398895899595 
MAPE:	 6.776737847872761

MIDPOINT
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 46.490023595118274 
RMSE:	 6.818359303756166 
MAPE:	 5.538801606657957

T3
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	51.12% Accuracy
MSE:	 57.75776139981352 
RMSE:	 7.59985272224492 
MAPE:	 6.172107202063374

TEMA
Prediction vs Close:		50.75% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 61.81638170069383 
RMSE:	 7.862339454684835 
MAPE:	 7.157520441443416
Runtime: mins: 12.264119731699997

Architecture Used

In [ ]:
from google.colab import files
import cv2
uploaded = files.upload()
Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to enable. 
Saving Experiment3.png to Experiment3 (1).png
In [ ]:
img = cv2.imread('Experiment3.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)
Out[ ]:
<matplotlib.image.AxesImage at 0x7fb3f5496390>

Model Plots

In [103]:
with open('simulation3_data.json') as json_file:
    simulation3 = json.load(json_file)
fileimg = 'Experiment3'
In [104]:
for i in range(len(list(simulation3.keys()))):
  SIM = list(simulation3.keys())[i]
  plot_train(simulation3,SIM)
  plot_test(simulation3,SIM)

----- Train RMSE for SMA ----- 8.930823939228564
----- Train_MSE_LSTM for SMA ----- 79.759616233498
----- Train MAE LSTM for SMA ----- 7.745279391393028

----- Test RMSE for SMA----- 11.134133576764116
----- Test_MSE_LSTM for SMA----- 123.96893050522607
----- Test_MAE_LSTM for SMA----- 9.602398807260117

----- Train RMSE for EMA ----- 10.565146653068828
----- Train_MSE_LSTM for EMA ----- 111.62232380085146
----- Train MAE LSTM for EMA ----- 9.411117943188193

----- Test RMSE for EMA----- 7.994952284204596
----- Test_MSE_LSTM for EMA----- 63.919262026708296
----- Test_MAE_LSTM for EMA----- 6.479287961204322

----- Train RMSE for WMA ----- 10.832264554488258
----- Train_MSE_LSTM for WMA ----- 117.3379553784227
----- Train MAE LSTM for WMA ----- 9.744005795817195

----- Test RMSE for WMA----- 4.9649832126431495
----- Test_MSE_LSTM for WMA----- 24.651058301828286
----- Test_MAE_LSTM for WMA----- 3.9308905500983484

----- Train RMSE for DEMA ----- 12.56480336163703
----- Train_MSE_LSTM for DEMA ----- 157.8742835166052
----- Train MAE LSTM for DEMA ----- 11.433644929764755

----- Test RMSE for DEMA----- 12.524518989134338
----- Test_MSE_LSTM for DEMA----- 156.8635759091866
----- Test_MAE_LSTM for DEMA----- 11.387412907589542

----- Train RMSE for KAMA ----- 10.593820426171298
----- Train_MSE_LSTM for KAMA ----- 112.22903122196423
----- Train MAE LSTM for KAMA ----- 9.500249049755386

----- Test RMSE for KAMA----- 7.69398895899595
----- Test_MSE_LSTM for KAMA----- 59.19746610115158
----- Test_MAE_LSTM for KAMA----- 6.776737847872761

----- Train RMSE for MIDPOINT ----- 9.5736663214708
----- Train_MSE_LSTM for MIDPOINT ----- 91.65508683486424
----- Train MAE LSTM for MIDPOINT ----- 8.498581498536272

----- Test RMSE for MIDPOINT----- 6.818359303756166
----- Test_MSE_LSTM for MIDPOINT----- 46.490023595118274
----- Test_MAE_LSTM for MIDPOINT----- 5.538801606657957

----- Train RMSE for T3 ----- 12.412205084380062
----- Train_MSE_LSTM for T3 ----- 154.06283505671027
----- Train MAE LSTM for T3 ----- 11.289339550955239

----- Test RMSE for T3----- 7.59985272224492
----- Test_MSE_LSTM for T3----- 57.75776139981352
----- Test_MAE_LSTM for T3----- 6.172107202063374

----- Train RMSE for TEMA ----- 7.318337811184663
----- Train_MSE_LSTM for TEMA ----- 53.55806831861513
----- Train MAE LSTM for TEMA ----- 4.992749833584864

----- Test RMSE for TEMA----- 7.862339454684835
----- Test_MSE_LSTM for TEMA----- 61.81638170069383
----- Test_MAE_LSTM for TEMA----- 7.157520441443416

Univariate Arima Multistep MutiVariate LSTM Hybrid Model Experiment 4

From the above experiments it is evident that with Higher moving averages the loss plots show unreoresented data and underfitting, hence keeping only the MA's that have smaller periods like T3 OR TRIMA. Going forward EMA, WMA & DEMA will be ignored.

In [ ]:
def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # # Option 1
    # # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()




    # # Option 3
    # # define custom activation
    # # 
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    model = Sequential()
    model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(input_dim, feature_size)))
    model.add(LSTM(units=int(lstm_len/2)))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='mean_squared_error', optimizer='adam')
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM4.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = (y_scaler.inverse_transform(predictiontr)-det).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte =( y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te
In [ ]:
if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation4 = {}
    imgfile = 'Experiment4'
    for ma in optimized_period:
              print(ma)
              print(functions[ma])
              print ( int( optimized_period[ma]))
            # if ma == 'SMA':
              low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
              low_vol = low_vol.fillna(0)
              low_vol_data = df['close']
              high_vol = pd.DataFrame()
              df2 = df.copy()
              for i in df2.columns:
                if i in low_vol.columns:
                  high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
              high_vol_data = df['close']
              ## *****************************************************
              # Generate ARIMA and LSTM predictions
              print('\nWorking on ' + ma + ' predictions')
              try:
                print('parameters used : ', train_len, test_len)
                low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima(low_vol,low_vol_data, train_len, test_len)
              except:
                  print('ARIMA error, skipping to next MA type')
                  continue
              Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
              final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
              mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
              rmse_ftr = mse_ftr ** 0.5
              mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
              mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

              final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
              mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
              rmse = mse ** 0.5
              mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              # Generate prediction accuracy
              actual = df['close'].tail(test_len).values
              result_1 = []
              result_2 = []
              for i in range(1, len(final_prediction)):
                  # Compare prediction to previous close price
                  if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                      result_1.append(1)
                  elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                      result_1.append(1)
                  else:
                      result_1.append(0)

                  # Compare prediction to previous prediction
                  if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                      result_2.append(1)
                  elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                      result_2.append(1)
                  else:
                      result_2.append(0)

              accuracy_1 = np.mean(result_1)
              accuracy_2 = np.mean(result_2)

              simulation4[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                            'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                            'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                            'rmse': rmse_ftr, 'mae' : mae_ftr},
                                'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                          'rmse': rmse, 'mae': mae },
                                'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

              # save simulation data here as checkpoint
              with open('simulation4_data.json', 'w') as fp:
                  json.dump(simulation4, fp)

              for ma in simulation4.keys():
                  print('\n' + ma)
                  print('Prediction vs Close:\t\t' + str(round(100*simulation4[ma]['accuracy']['prediction vs close'], 2))
                        + '% Accuracy')
                  print('Prediction vs Prediction:\t' + str(round(100*simulation4[ma]['accuracy']['prediction vs prediction'], 2))
                        + '% Accuracy')
                  print('MSE:\t', simulation4[ma]['final']['mse'],
                        '\nRMSE:\t', simulation4[ma]['final']['rmse'],
                        '\nMAPE:\t', simulation4[ma]['final']['mae'])#,
                        # '\nMAPE:\t', simulation[ma]['final']['mape'])
            # else:
            #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.39 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4157.020, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3687.148, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.15 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3458.651, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3322.133, Time=0.06 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.56 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.58 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3324.133, Time=0.17 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.034 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1657.067
Date:                Sun, 12 Dec 2021   AIC                           3322.133
Time:                        13:58:09   BIC                           3340.897
Sample:                             0   HQIC                          3329.339
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1966      0.003   -387.226      0.000      -1.203      -1.191
ar.L2         -0.8952      0.006   -138.692      0.000      -0.908      -0.883
ar.L3         -0.3968      0.006    -68.284      0.000      -0.408      -0.385
sigma2         3.5858      0.017    214.535      0.000       3.553       3.619
===================================================================================
Ljung-Box (L1) (Q):                  14.47   Jarque-Bera (JB):           2428881.42
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       271.99
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04752, saving model to LSTM4.h5
48/48 - 5s - loss: 1.3281 - val_loss: 0.0475 - lr: 0.0010 - 5s/epoch - 98ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04752
48/48 - 0s - loss: 1.1972 - val_loss: 0.0492 - lr: 0.0010 - 309ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04752
48/48 - 0s - loss: 1.0857 - val_loss: 0.0527 - lr: 0.0010 - 310ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04752
48/48 - 0s - loss: 1.0040 - val_loss: 0.0580 - lr: 0.0010 - 307ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.9411 - val_loss: 0.0646 - lr: 0.0010 - 323ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8869 - val_loss: 0.0711 - lr: 0.0010 - 311ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8549 - val_loss: 0.0718 - lr: 1.0000e-04 - 308ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8502 - val_loss: 0.0724 - lr: 1.0000e-04 - 311ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8456 - val_loss: 0.0730 - lr: 1.0000e-04 - 302ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8410 - val_loss: 0.0737 - lr: 1.0000e-04 - 313ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8366 - val_loss: 0.0744 - lr: 1.0000e-04 - 317ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8339 - val_loss: 0.0744 - lr: 1.0000e-05 - 307ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8334 - val_loss: 0.0745 - lr: 1.0000e-05 - 310ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8330 - val_loss: 0.0746 - lr: 1.0000e-05 - 322ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8326 - val_loss: 0.0747 - lr: 1.0000e-05 - 307ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8321 - val_loss: 0.0747 - lr: 1.0000e-05 - 319ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8317 - val_loss: 0.0748 - lr: 1.0000e-05 - 315ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8312 - val_loss: 0.0749 - lr: 1.0000e-05 - 295ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8308 - val_loss: 0.0750 - lr: 1.0000e-05 - 299ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8303 - val_loss: 0.0751 - lr: 1.0000e-05 - 304ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8298 - val_loss: 0.0751 - lr: 1.0000e-05 - 313ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8294 - val_loss: 0.0752 - lr: 1.0000e-05 - 298ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8289 - val_loss: 0.0753 - lr: 1.0000e-05 - 318ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8285 - val_loss: 0.0754 - lr: 1.0000e-05 - 305ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8280 - val_loss: 0.0755 - lr: 1.0000e-05 - 310ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8275 - val_loss: 0.0756 - lr: 1.0000e-05 - 296ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8271 - val_loss: 0.0757 - lr: 1.0000e-05 - 313ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8266 - val_loss: 0.0758 - lr: 1.0000e-05 - 315ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8261 - val_loss: 0.0758 - lr: 1.0000e-05 - 318ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8257 - val_loss: 0.0759 - lr: 1.0000e-05 - 315ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8252 - val_loss: 0.0760 - lr: 1.0000e-05 - 308ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8248 - val_loss: 0.0761 - lr: 1.0000e-05 - 304ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8243 - val_loss: 0.0762 - lr: 1.0000e-05 - 326ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8238 - val_loss: 0.0763 - lr: 1.0000e-05 - 304ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8234 - val_loss: 0.0764 - lr: 1.0000e-05 - 294ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8229 - val_loss: 0.0765 - lr: 1.0000e-05 - 306ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8224 - val_loss: 0.0766 - lr: 1.0000e-05 - 314ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8220 - val_loss: 0.0767 - lr: 1.0000e-05 - 295ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8215 - val_loss: 0.0768 - lr: 1.0000e-05 - 312ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8210 - val_loss: 0.0769 - lr: 1.0000e-05 - 308ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8206 - val_loss: 0.0770 - lr: 1.0000e-05 - 301ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8201 - val_loss: 0.0771 - lr: 1.0000e-05 - 311ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8196 - val_loss: 0.0772 - lr: 1.0000e-05 - 318ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8192 - val_loss: 0.0773 - lr: 1.0000e-05 - 313ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8187 - val_loss: 0.0774 - lr: 1.0000e-05 - 302ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8183 - val_loss: 0.0775 - lr: 1.0000e-05 - 320ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8178 - val_loss: 0.0777 - lr: 1.0000e-05 - 308ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8173 - val_loss: 0.0778 - lr: 1.0000e-05 - 307ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8169 - val_loss: 0.0779 - lr: 1.0000e-05 - 319ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8164 - val_loss: 0.0780 - lr: 1.0000e-05 - 309ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04752
48/48 - 0s - loss: 0.8160 - val_loss: 0.0781 - lr: 1.0000e-05 - 304ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 22.0961825771905 
RMSE:	 4.700657674963207 
MAPE:	 3.7488296078488137
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4231.556, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3761.238, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.18 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3532.227, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3394.496, Time=0.11 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.02 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.52 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3396.496, Time=0.24 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.543 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1693.248
Date:                Sun, 12 Dec 2021   AIC                           3394.496
Time:                        13:59:42   BIC                           3413.260
Sample:                             0   HQIC                          3401.702
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.569      0.000      -1.204      -1.192
ar.L2         -0.8976      0.006   -139.811      0.000      -0.910      -0.885
ar.L3         -0.3984      0.006    -68.662      0.000      -0.410      -0.387
sigma2         3.9230      0.018    215.372      0.000       3.887       3.959
===================================================================================
Ljung-Box (L1) (Q):                  14.54   Jarque-Bera (JB):           2462173.05
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.82
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04897, saving model to LSTM4.h5
16/16 - 5s - loss: 1.3851 - val_loss: 0.0490 - lr: 0.0010 - 5s/epoch - 286ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.3596 - val_loss: 0.0500 - lr: 0.0010 - 125ms/epoch - 8ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.3341 - val_loss: 0.0511 - lr: 0.0010 - 126ms/epoch - 8ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.3075 - val_loss: 0.0520 - lr: 0.0010 - 121ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2797 - val_loss: 0.0529 - lr: 0.0010 - 116ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2518 - val_loss: 0.0539 - lr: 0.0010 - 121ms/epoch - 8ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2342 - val_loss: 0.0540 - lr: 1.0000e-04 - 117ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2316 - val_loss: 0.0541 - lr: 1.0000e-04 - 119ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2290 - val_loss: 0.0542 - lr: 1.0000e-04 - 116ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2265 - val_loss: 0.0543 - lr: 1.0000e-04 - 124ms/epoch - 8ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2240 - val_loss: 0.0544 - lr: 1.0000e-04 - 129ms/epoch - 8ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2223 - val_loss: 0.0545 - lr: 1.0000e-05 - 120ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2221 - val_loss: 0.0545 - lr: 1.0000e-05 - 118ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2219 - val_loss: 0.0545 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2216 - val_loss: 0.0545 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2214 - val_loss: 0.0545 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2211 - val_loss: 0.0545 - lr: 1.0000e-05 - 123ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2209 - val_loss: 0.0545 - lr: 1.0000e-05 - 123ms/epoch - 8ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2206 - val_loss: 0.0545 - lr: 1.0000e-05 - 124ms/epoch - 8ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2204 - val_loss: 0.0545 - lr: 1.0000e-05 - 120ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2201 - val_loss: 0.0546 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2199 - val_loss: 0.0546 - lr: 1.0000e-05 - 120ms/epoch - 8ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2196 - val_loss: 0.0546 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2194 - val_loss: 0.0546 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2192 - val_loss: 0.0546 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2189 - val_loss: 0.0546 - lr: 1.0000e-05 - 118ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2187 - val_loss: 0.0546 - lr: 1.0000e-05 - 123ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2184 - val_loss: 0.0546 - lr: 1.0000e-05 - 122ms/epoch - 8ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2182 - val_loss: 0.0547 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2179 - val_loss: 0.0547 - lr: 1.0000e-05 - 123ms/epoch - 8ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2177 - val_loss: 0.0547 - lr: 1.0000e-05 - 120ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2174 - val_loss: 0.0547 - lr: 1.0000e-05 - 120ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2172 - val_loss: 0.0547 - lr: 1.0000e-05 - 127ms/epoch - 8ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2170 - val_loss: 0.0547 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2167 - val_loss: 0.0547 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2165 - val_loss: 0.0547 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2162 - val_loss: 0.0547 - lr: 1.0000e-05 - 118ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2160 - val_loss: 0.0548 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2157 - val_loss: 0.0548 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2155 - val_loss: 0.0548 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2153 - val_loss: 0.0548 - lr: 1.0000e-05 - 123ms/epoch - 8ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2150 - val_loss: 0.0548 - lr: 1.0000e-05 - 122ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2148 - val_loss: 0.0548 - lr: 1.0000e-05 - 126ms/epoch - 8ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2145 - val_loss: 0.0548 - lr: 1.0000e-05 - 128ms/epoch - 8ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2143 - val_loss: 0.0548 - lr: 1.0000e-05 - 122ms/epoch - 8ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2140 - val_loss: 0.0549 - lr: 1.0000e-05 - 127ms/epoch - 8ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2138 - val_loss: 0.0549 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2136 - val_loss: 0.0549 - lr: 1.0000e-05 - 120ms/epoch - 8ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2133 - val_loss: 0.0549 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2131 - val_loss: 0.0549 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04897
16/16 - 0s - loss: 1.2128 - val_loss: 0.0549 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 22.0961825771905 
RMSE:	 4.700657674963207 
MAPE:	 3.7488296078488137

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.69312385194829 
RMSE:	 6.057484944426053 
MAPE:	 4.755707959713801
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4264.089, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3793.930, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.18 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3564.923, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3427.258, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.49 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.35 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3429.258, Time=0.14 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.749 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1709.629
Date:                Sun, 12 Dec 2021   AIC                           3427.258
Time:                        14:01:02   BIC                           3446.021
Sample:                             0   HQIC                          3434.464
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1981      0.003   -389.386      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.699      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.737      0.000      -0.410      -0.387
sigma2         4.0860      0.019    215.311      0.000       4.049       4.123
===================================================================================
Ljung-Box (L1) (Q):                  14.57   Jarque-Bera (JB):           2460901.70
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.75
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.03613, saving model to LSTM4.h5
17/17 - 5s - loss: 1.4348 - val_loss: 0.0361 - lr: 0.0010 - 5s/epoch - 304ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.4035 - val_loss: 0.0367 - lr: 0.0010 - 295ms/epoch - 17ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.3693 - val_loss: 0.0376 - lr: 0.0010 - 278ms/epoch - 16ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.3307 - val_loss: 0.0388 - lr: 0.0010 - 128ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.2897 - val_loss: 0.0401 - lr: 0.0010 - 134ms/epoch - 8ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.2464 - val_loss: 0.0413 - lr: 0.0010 - 133ms/epoch - 8ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.2140 - val_loss: 0.0414 - lr: 1.0000e-04 - 128ms/epoch - 8ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.2087 - val_loss: 0.0414 - lr: 1.0000e-04 - 127ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.2035 - val_loss: 0.0415 - lr: 1.0000e-04 - 128ms/epoch - 8ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1983 - val_loss: 0.0416 - lr: 1.0000e-04 - 132ms/epoch - 8ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1931 - val_loss: 0.0416 - lr: 1.0000e-04 - 134ms/epoch - 8ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1897 - val_loss: 0.0416 - lr: 1.0000e-05 - 128ms/epoch - 8ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1892 - val_loss: 0.0416 - lr: 1.0000e-05 - 126ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1887 - val_loss: 0.0416 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1882 - val_loss: 0.0416 - lr: 1.0000e-05 - 124ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1877 - val_loss: 0.0416 - lr: 1.0000e-05 - 124ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1872 - val_loss: 0.0417 - lr: 1.0000e-05 - 128ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1867 - val_loss: 0.0417 - lr: 1.0000e-05 - 132ms/epoch - 8ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1862 - val_loss: 0.0417 - lr: 1.0000e-05 - 132ms/epoch - 8ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1858 - val_loss: 0.0417 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1853 - val_loss: 0.0417 - lr: 1.0000e-05 - 128ms/epoch - 8ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1848 - val_loss: 0.0417 - lr: 1.0000e-05 - 124ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1843 - val_loss: 0.0417 - lr: 1.0000e-05 - 127ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1839 - val_loss: 0.0417 - lr: 1.0000e-05 - 124ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1834 - val_loss: 0.0417 - lr: 1.0000e-05 - 127ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1829 - val_loss: 0.0417 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1825 - val_loss: 0.0417 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1820 - val_loss: 0.0417 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1815 - val_loss: 0.0417 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1810 - val_loss: 0.0417 - lr: 1.0000e-05 - 125ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1806 - val_loss: 0.0418 - lr: 1.0000e-05 - 123ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1801 - val_loss: 0.0418 - lr: 1.0000e-05 - 128ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1796 - val_loss: 0.0418 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1792 - val_loss: 0.0418 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1787 - val_loss: 0.0418 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1782 - val_loss: 0.0418 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1778 - val_loss: 0.0418 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1773 - val_loss: 0.0418 - lr: 1.0000e-05 - 133ms/epoch - 8ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1769 - val_loss: 0.0418 - lr: 1.0000e-05 - 124ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1764 - val_loss: 0.0418 - lr: 1.0000e-05 - 137ms/epoch - 8ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1759 - val_loss: 0.0418 - lr: 1.0000e-05 - 134ms/epoch - 8ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1755 - val_loss: 0.0418 - lr: 1.0000e-05 - 123ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1750 - val_loss: 0.0418 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1745 - val_loss: 0.0418 - lr: 1.0000e-05 - 126ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1741 - val_loss: 0.0418 - lr: 1.0000e-05 - 122ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1736 - val_loss: 0.0419 - lr: 1.0000e-05 - 129ms/epoch - 8ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1731 - val_loss: 0.0419 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1727 - val_loss: 0.0419 - lr: 1.0000e-05 - 136ms/epoch - 8ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1722 - val_loss: 0.0419 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1717 - val_loss: 0.0419 - lr: 1.0000e-05 - 124ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03613
17/17 - 0s - loss: 1.1713 - val_loss: 0.0419 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 22.0961825771905 
RMSE:	 4.700657674963207 
MAPE:	 3.7488296078488137

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.69312385194829 
RMSE:	 6.057484944426053 
MAPE:	 4.755707959713801

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 61.47074835668693 
RMSE:	 7.8403283321992925 
MAPE:	 6.468176158698829
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4436.126, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3965.317, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.28 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3736.589, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3598.951, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.17 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.73 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3600.951, Time=0.15 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.921 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1795.475
Date:                Sun, 12 Dec 2021   AIC                           3598.951
Time:                        14:02:19   BIC                           3617.714
Sample:                             0   HQIC                          3606.157
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1983      0.003   -389.581      0.000      -1.204      -1.192
ar.L2         -0.8973      0.006   -139.732      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.649      0.000      -0.410      -0.387
sigma2         5.0573      0.023    215.292      0.000       5.011       5.103
===================================================================================
Ljung-Box (L1) (Q):                  14.41   Jarque-Bera (JB):           2460553.80
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.89
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.07261, saving model to LSTM4.h5
10/10 - 5s - loss: 1.5344 - val_loss: 0.0726 - lr: 0.0010 - 5s/epoch - 458ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.07261 to 0.07257, saving model to LSTM4.h5
10/10 - 0s - loss: 1.5110 - val_loss: 0.0726 - lr: 0.0010 - 101ms/epoch - 10ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.07257 to 0.07170, saving model to LSTM4.h5
10/10 - 0s - loss: 1.4835 - val_loss: 0.0717 - lr: 0.0010 - 100ms/epoch - 10ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.07170 to 0.07007, saving model to LSTM4.h5
10/10 - 0s - loss: 1.4466 - val_loss: 0.0701 - lr: 0.0010 - 106ms/epoch - 11ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.07007 to 0.06801, saving model to LSTM4.h5
10/10 - 0s - loss: 1.3954 - val_loss: 0.0680 - lr: 0.0010 - 108ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.06801 to 0.06600, saving model to LSTM4.h5
10/10 - 0s - loss: 1.3267 - val_loss: 0.0660 - lr: 0.0010 - 103ms/epoch - 10ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.06600 to 0.06432, saving model to LSTM4.h5
10/10 - 0s - loss: 1.2426 - val_loss: 0.0643 - lr: 0.0010 - 110ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.06432 to 0.06309, saving model to LSTM4.h5
10/10 - 0s - loss: 1.1568 - val_loss: 0.0631 - lr: 0.0010 - 110ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.06309 to 0.06233, saving model to LSTM4.h5
10/10 - 0s - loss: 1.0839 - val_loss: 0.0623 - lr: 0.0010 - 108ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.06233 to 0.06201, saving model to LSTM4.h5
10/10 - 0s - loss: 1.0279 - val_loss: 0.0620 - lr: 0.0010 - 109ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.9851 - val_loss: 0.0620 - lr: 0.0010 - 85ms/epoch - 9ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.9513 - val_loss: 0.0623 - lr: 0.0010 - 87ms/epoch - 9ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.9241 - val_loss: 0.0628 - lr: 0.0010 - 91ms/epoch - 9ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.9016 - val_loss: 0.0634 - lr: 0.0010 - 83ms/epoch - 8ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00015: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8828 - val_loss: 0.0641 - lr: 0.0010 - 88ms/epoch - 9ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8715 - val_loss: 0.0641 - lr: 1.0000e-04 - 82ms/epoch - 8ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8700 - val_loss: 0.0642 - lr: 1.0000e-04 - 90ms/epoch - 9ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8686 - val_loss: 0.0643 - lr: 1.0000e-04 - 91ms/epoch - 9ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8672 - val_loss: 0.0644 - lr: 1.0000e-04 - 86ms/epoch - 9ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00020: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8658 - val_loss: 0.0645 - lr: 1.0000e-04 - 91ms/epoch - 9ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8648 - val_loss: 0.0645 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8647 - val_loss: 0.0645 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8645 - val_loss: 0.0645 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8644 - val_loss: 0.0645 - lr: 1.0000e-05 - 85ms/epoch - 8ms/step
Epoch 25/500

Epoch 00025: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00025: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8643 - val_loss: 0.0645 - lr: 1.0000e-05 - 85ms/epoch - 9ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8641 - val_loss: 0.0645 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8640 - val_loss: 0.0645 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8638 - val_loss: 0.0645 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8637 - val_loss: 0.0645 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8636 - val_loss: 0.0645 - lr: 1.0000e-05 - 91ms/epoch - 9ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8634 - val_loss: 0.0646 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8633 - val_loss: 0.0646 - lr: 1.0000e-05 - 85ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8631 - val_loss: 0.0646 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8630 - val_loss: 0.0646 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8628 - val_loss: 0.0646 - lr: 1.0000e-05 - 83ms/epoch - 8ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8627 - val_loss: 0.0646 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8625 - val_loss: 0.0646 - lr: 1.0000e-05 - 84ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8624 - val_loss: 0.0646 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8622 - val_loss: 0.0646 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8621 - val_loss: 0.0646 - lr: 1.0000e-05 - 85ms/epoch - 9ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8620 - val_loss: 0.0647 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8618 - val_loss: 0.0647 - lr: 1.0000e-05 - 91ms/epoch - 9ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8617 - val_loss: 0.0647 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8615 - val_loss: 0.0647 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8614 - val_loss: 0.0647 - lr: 1.0000e-05 - 92ms/epoch - 9ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8612 - val_loss: 0.0647 - lr: 1.0000e-05 - 84ms/epoch - 8ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8611 - val_loss: 0.0647 - lr: 1.0000e-05 - 84ms/epoch - 8ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8609 - val_loss: 0.0647 - lr: 1.0000e-05 - 85ms/epoch - 9ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8608 - val_loss: 0.0647 - lr: 1.0000e-05 - 92ms/epoch - 9ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8606 - val_loss: 0.0647 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8605 - val_loss: 0.0647 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8603 - val_loss: 0.0648 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8602 - val_loss: 0.0648 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8600 - val_loss: 0.0648 - lr: 1.0000e-05 - 92ms/epoch - 9ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8598 - val_loss: 0.0648 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8597 - val_loss: 0.0648 - lr: 1.0000e-05 - 83ms/epoch - 8ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8595 - val_loss: 0.0648 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8594 - val_loss: 0.0648 - lr: 1.0000e-05 - 95ms/epoch - 9ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8592 - val_loss: 0.0648 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.06201
10/10 - 0s - loss: 0.8591 - val_loss: 0.0648 - lr: 1.0000e-05 - 91ms/epoch - 9ms/step
Epoch 00060: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 22.0961825771905 
RMSE:	 4.700657674963207 
MAPE:	 3.7488296078488137

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.69312385194829 
RMSE:	 6.057484944426053 
MAPE:	 4.755707959713801

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 61.47074835668693 
RMSE:	 7.8403283321992925 
MAPE:	 6.468176158698829

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 114.21230424130383 
RMSE:	 10.687015684525958 
MAPE:	 9.305044543155903
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.32 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4190.464, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3724.371, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.20 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3494.154, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3357.435, Time=0.11 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.43 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.58 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3359.435, Time=0.26 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.022 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1674.717
Date:                Sun, 12 Dec 2021   AIC                           3357.435
Time:                        14:03:40   BIC                           3376.198
Sample:                             0   HQIC                          3364.641
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1955      0.003   -381.246      0.000      -1.202      -1.189
ar.L2         -0.8964      0.007   -135.835      0.000      -0.909      -0.883
ar.L3         -0.3971      0.006    -67.229      0.000      -0.409      -0.385
sigma2         3.7466      0.018    211.623      0.000       3.712       3.781
===================================================================================
Ljung-Box (L1) (Q):                  14.20   Jarque-Bera (JB):           2338363.32
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             3.76
Prob(H) (two-sided):                  0.00   Kurtosis:                       266.93
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05179, saving model to LSTM4.h5
45/45 - 5s - loss: 1.4217 - val_loss: 0.0518 - lr: 0.0010 - 5s/epoch - 109ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.3716 - val_loss: 0.0538 - lr: 0.0010 - 296ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.3061 - val_loss: 0.0555 - lr: 0.0010 - 289ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.2392 - val_loss: 0.0574 - lr: 0.0010 - 287ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.1760 - val_loss: 0.0601 - lr: 0.0010 - 300ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.1169 - val_loss: 0.0640 - lr: 0.0010 - 298ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0830 - val_loss: 0.0644 - lr: 1.0000e-04 - 292ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0781 - val_loss: 0.0649 - lr: 1.0000e-04 - 290ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0734 - val_loss: 0.0653 - lr: 1.0000e-04 - 302ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0688 - val_loss: 0.0658 - lr: 1.0000e-04 - 293ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0643 - val_loss: 0.0662 - lr: 1.0000e-04 - 299ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0615 - val_loss: 0.0663 - lr: 1.0000e-05 - 297ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0611 - val_loss: 0.0663 - lr: 1.0000e-05 - 283ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0606 - val_loss: 0.0664 - lr: 1.0000e-05 - 291ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0602 - val_loss: 0.0664 - lr: 1.0000e-05 - 299ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0598 - val_loss: 0.0665 - lr: 1.0000e-05 - 306ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0593 - val_loss: 0.0665 - lr: 1.0000e-05 - 287ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0589 - val_loss: 0.0666 - lr: 1.0000e-05 - 298ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0585 - val_loss: 0.0666 - lr: 1.0000e-05 - 291ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0580 - val_loss: 0.0667 - lr: 1.0000e-05 - 301ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0576 - val_loss: 0.0667 - lr: 1.0000e-05 - 295ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0572 - val_loss: 0.0668 - lr: 1.0000e-05 - 301ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0567 - val_loss: 0.0668 - lr: 1.0000e-05 - 292ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0563 - val_loss: 0.0669 - lr: 1.0000e-05 - 290ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0558 - val_loss: 0.0669 - lr: 1.0000e-05 - 293ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0554 - val_loss: 0.0670 - lr: 1.0000e-05 - 294ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0550 - val_loss: 0.0670 - lr: 1.0000e-05 - 298ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0545 - val_loss: 0.0671 - lr: 1.0000e-05 - 287ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0541 - val_loss: 0.0671 - lr: 1.0000e-05 - 307ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0537 - val_loss: 0.0672 - lr: 1.0000e-05 - 272ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0532 - val_loss: 0.0673 - lr: 1.0000e-05 - 293ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0528 - val_loss: 0.0673 - lr: 1.0000e-05 - 287ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0524 - val_loss: 0.0674 - lr: 1.0000e-05 - 315ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0519 - val_loss: 0.0674 - lr: 1.0000e-05 - 290ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0515 - val_loss: 0.0675 - lr: 1.0000e-05 - 301ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0511 - val_loss: 0.0675 - lr: 1.0000e-05 - 285ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0506 - val_loss: 0.0676 - lr: 1.0000e-05 - 298ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0502 - val_loss: 0.0676 - lr: 1.0000e-05 - 286ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0498 - val_loss: 0.0677 - lr: 1.0000e-05 - 311ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0494 - val_loss: 0.0678 - lr: 1.0000e-05 - 292ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0489 - val_loss: 0.0678 - lr: 1.0000e-05 - 291ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0485 - val_loss: 0.0679 - lr: 1.0000e-05 - 302ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0481 - val_loss: 0.0679 - lr: 1.0000e-05 - 293ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0476 - val_loss: 0.0680 - lr: 1.0000e-05 - 281ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0472 - val_loss: 0.0680 - lr: 1.0000e-05 - 281ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0468 - val_loss: 0.0681 - lr: 1.0000e-05 - 291ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0464 - val_loss: 0.0682 - lr: 1.0000e-05 - 295ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0459 - val_loss: 0.0682 - lr: 1.0000e-05 - 297ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0455 - val_loss: 0.0683 - lr: 1.0000e-05 - 295ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0451 - val_loss: 0.0683 - lr: 1.0000e-05 - 287ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05179
45/45 - 0s - loss: 1.0447 - val_loss: 0.0684 - lr: 1.0000e-05 - 280ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 22.0961825771905 
RMSE:	 4.700657674963207 
MAPE:	 3.7488296078488137

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.69312385194829 
RMSE:	 6.057484944426053 
MAPE:	 4.755707959713801

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 61.47074835668693 
RMSE:	 7.8403283321992925 
MAPE:	 6.468176158698829

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 114.21230424130383 
RMSE:	 10.687015684525958 
MAPE:	 9.305044543155903

KAMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 21.57120658320832 
RMSE:	 4.6444813040002995 
MAPE:	 3.6837316829247877
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.32 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4212.289, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3747.746, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.16 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3523.401, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3387.759, Time=0.12 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.51 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.65 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3389.758, Time=0.16 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.035 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1689.879
Date:                Sun, 12 Dec 2021   AIC                           3387.759
Time:                        14:05:16   BIC                           3406.522
Sample:                             0   HQIC                          3394.964
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1878      0.003   -345.315      0.000      -1.195      -1.181
ar.L2         -0.8876      0.007   -121.809      0.000      -0.902      -0.873
ar.L3         -0.3957      0.007    -60.127      0.000      -0.409      -0.383
sigma2         3.8904      0.020    193.404      0.000       3.851       3.930
===================================================================================
Ljung-Box (L1) (Q):                  13.21   Jarque-Bera (JB):           1659080.01
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.08   Skew:                             3.28
Prob(H) (two-sided):                  0.00   Kurtosis:                       225.31
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.06664, saving model to LSTM4.h5
58/58 - 6s - loss: 1.4317 - val_loss: 0.0666 - lr: 0.0010 - 6s/epoch - 96ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.06664
58/58 - 0s - loss: 1.2922 - val_loss: 0.0704 - lr: 0.0010 - 382ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.06664
58/58 - 0s - loss: 1.0995 - val_loss: 0.0737 - lr: 0.0010 - 381ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.9549 - val_loss: 0.0793 - lr: 0.0010 - 368ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.8739 - val_loss: 0.0852 - lr: 0.0010 - 385ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.8200 - val_loss: 0.0912 - lr: 0.0010 - 357ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7942 - val_loss: 0.0918 - lr: 1.0000e-04 - 367ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7906 - val_loss: 0.0924 - lr: 1.0000e-04 - 354ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7870 - val_loss: 0.0930 - lr: 1.0000e-04 - 375ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7835 - val_loss: 0.0937 - lr: 1.0000e-04 - 367ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7800 - val_loss: 0.0944 - lr: 1.0000e-04 - 361ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7778 - val_loss: 0.0944 - lr: 1.0000e-05 - 366ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7775 - val_loss: 0.0945 - lr: 1.0000e-05 - 379ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7772 - val_loss: 0.0946 - lr: 1.0000e-05 - 380ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7768 - val_loss: 0.0947 - lr: 1.0000e-05 - 381ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7764 - val_loss: 0.0947 - lr: 1.0000e-05 - 366ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7761 - val_loss: 0.0948 - lr: 1.0000e-05 - 383ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7757 - val_loss: 0.0949 - lr: 1.0000e-05 - 372ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7753 - val_loss: 0.0950 - lr: 1.0000e-05 - 363ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7750 - val_loss: 0.0950 - lr: 1.0000e-05 - 366ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7746 - val_loss: 0.0951 - lr: 1.0000e-05 - 377ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7742 - val_loss: 0.0952 - lr: 1.0000e-05 - 366ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7739 - val_loss: 0.0953 - lr: 1.0000e-05 - 373ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7735 - val_loss: 0.0954 - lr: 1.0000e-05 - 360ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7731 - val_loss: 0.0954 - lr: 1.0000e-05 - 378ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7727 - val_loss: 0.0955 - lr: 1.0000e-05 - 381ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7723 - val_loss: 0.0956 - lr: 1.0000e-05 - 385ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7720 - val_loss: 0.0957 - lr: 1.0000e-05 - 373ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7716 - val_loss: 0.0958 - lr: 1.0000e-05 - 367ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7712 - val_loss: 0.0959 - lr: 1.0000e-05 - 372ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7708 - val_loss: 0.0960 - lr: 1.0000e-05 - 367ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7704 - val_loss: 0.0960 - lr: 1.0000e-05 - 376ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7700 - val_loss: 0.0961 - lr: 1.0000e-05 - 377ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7696 - val_loss: 0.0962 - lr: 1.0000e-05 - 361ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7693 - val_loss: 0.0963 - lr: 1.0000e-05 - 363ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7689 - val_loss: 0.0964 - lr: 1.0000e-05 - 368ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7685 - val_loss: 0.0965 - lr: 1.0000e-05 - 353ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7681 - val_loss: 0.0966 - lr: 1.0000e-05 - 354ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7677 - val_loss: 0.0967 - lr: 1.0000e-05 - 366ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7673 - val_loss: 0.0967 - lr: 1.0000e-05 - 365ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7669 - val_loss: 0.0968 - lr: 1.0000e-05 - 366ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7665 - val_loss: 0.0969 - lr: 1.0000e-05 - 375ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7662 - val_loss: 0.0970 - lr: 1.0000e-05 - 373ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7658 - val_loss: 0.0971 - lr: 1.0000e-05 - 380ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7654 - val_loss: 0.0972 - lr: 1.0000e-05 - 366ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7650 - val_loss: 0.0973 - lr: 1.0000e-05 - 376ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7646 - val_loss: 0.0974 - lr: 1.0000e-05 - 377ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7642 - val_loss: 0.0975 - lr: 1.0000e-05 - 369ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7638 - val_loss: 0.0976 - lr: 1.0000e-05 - 371ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7634 - val_loss: 0.0977 - lr: 1.0000e-05 - 371ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.06664
58/58 - 0s - loss: 0.7631 - val_loss: 0.0977 - lr: 1.0000e-05 - 357ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 22.0961825771905 
RMSE:	 4.700657674963207 
MAPE:	 3.7488296078488137

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.69312385194829 
RMSE:	 6.057484944426053 
MAPE:	 4.755707959713801

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 61.47074835668693 
RMSE:	 7.8403283321992925 
MAPE:	 6.468176158698829

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 114.21230424130383 
RMSE:	 10.687015684525958 
MAPE:	 9.305044543155903

KAMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 21.57120658320832 
RMSE:	 4.6444813040002995 
MAPE:	 3.6837316829247877

MIDPOINT
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 17.38125304406819 
RMSE:	 4.169082997982673 
MAPE:	 3.3993243705608664
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.33 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4414.515, Time=0.02 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3944.062, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.26 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3715.173, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3577.471, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.75 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.47 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3579.471, Time=0.23 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.246 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1784.736
Date:                Sun, 12 Dec 2021   AIC                           3577.471
Time:                        14:06:56   BIC                           3596.235
Sample:                             0   HQIC                          3584.677
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.844      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.861      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.862      0.000      -0.410      -0.387
sigma2         4.9242      0.023    215.469      0.000       4.879       4.969
===================================================================================
Ljung-Box (L1) (Q):                  14.55   Jarque-Bera (JB):           2468024.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       274.15
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04821, saving model to LSTM4.h5
43/43 - 5s - loss: 1.3631 - val_loss: 0.0482 - lr: 0.0010 - 5s/epoch - 115ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04821
43/43 - 0s - loss: 1.1997 - val_loss: 0.0521 - lr: 0.0010 - 276ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04821
43/43 - 0s - loss: 1.0124 - val_loss: 0.0565 - lr: 0.0010 - 288ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.9002 - val_loss: 0.0608 - lr: 0.0010 - 287ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.8437 - val_loss: 0.0649 - lr: 0.0010 - 281ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.8075 - val_loss: 0.0691 - lr: 0.0010 - 280ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7899 - val_loss: 0.0695 - lr: 1.0000e-04 - 285ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7874 - val_loss: 0.0700 - lr: 1.0000e-04 - 294ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7848 - val_loss: 0.0704 - lr: 1.0000e-04 - 293ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7823 - val_loss: 0.0709 - lr: 1.0000e-04 - 273ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7797 - val_loss: 0.0714 - lr: 1.0000e-04 - 276ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7782 - val_loss: 0.0714 - lr: 1.0000e-05 - 288ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7779 - val_loss: 0.0715 - lr: 1.0000e-05 - 289ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7776 - val_loss: 0.0715 - lr: 1.0000e-05 - 275ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7774 - val_loss: 0.0716 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7771 - val_loss: 0.0716 - lr: 1.0000e-05 - 289ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7768 - val_loss: 0.0717 - lr: 1.0000e-05 - 280ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7766 - val_loss: 0.0718 - lr: 1.0000e-05 - 288ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7763 - val_loss: 0.0718 - lr: 1.0000e-05 - 303ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7760 - val_loss: 0.0719 - lr: 1.0000e-05 - 280ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7757 - val_loss: 0.0719 - lr: 1.0000e-05 - 283ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7754 - val_loss: 0.0720 - lr: 1.0000e-05 - 288ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7752 - val_loss: 0.0721 - lr: 1.0000e-05 - 290ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7749 - val_loss: 0.0721 - lr: 1.0000e-05 - 277ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7746 - val_loss: 0.0722 - lr: 1.0000e-05 - 290ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7743 - val_loss: 0.0723 - lr: 1.0000e-05 - 281ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7740 - val_loss: 0.0723 - lr: 1.0000e-05 - 284ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7737 - val_loss: 0.0724 - lr: 1.0000e-05 - 273ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7734 - val_loss: 0.0725 - lr: 1.0000e-05 - 289ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7731 - val_loss: 0.0726 - lr: 1.0000e-05 - 277ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7728 - val_loss: 0.0726 - lr: 1.0000e-05 - 288ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7725 - val_loss: 0.0727 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7722 - val_loss: 0.0728 - lr: 1.0000e-05 - 290ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7719 - val_loss: 0.0728 - lr: 1.0000e-05 - 279ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7716 - val_loss: 0.0729 - lr: 1.0000e-05 - 301ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7713 - val_loss: 0.0730 - lr: 1.0000e-05 - 286ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7710 - val_loss: 0.0731 - lr: 1.0000e-05 - 283ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7707 - val_loss: 0.0731 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7704 - val_loss: 0.0732 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7701 - val_loss: 0.0733 - lr: 1.0000e-05 - 281ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7698 - val_loss: 0.0734 - lr: 1.0000e-05 - 276ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7695 - val_loss: 0.0735 - lr: 1.0000e-05 - 276ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7692 - val_loss: 0.0735 - lr: 1.0000e-05 - 296ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7689 - val_loss: 0.0736 - lr: 1.0000e-05 - 273ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7686 - val_loss: 0.0737 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7683 - val_loss: 0.0738 - lr: 1.0000e-05 - 297ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7680 - val_loss: 0.0739 - lr: 1.0000e-05 - 290ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7677 - val_loss: 0.0740 - lr: 1.0000e-05 - 285ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7674 - val_loss: 0.0740 - lr: 1.0000e-05 - 299ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7671 - val_loss: 0.0741 - lr: 1.0000e-05 - 292ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04821
43/43 - 0s - loss: 0.7668 - val_loss: 0.0742 - lr: 1.0000e-05 - 287ms/epoch - 7ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 22.0961825771905 
RMSE:	 4.700657674963207 
MAPE:	 3.7488296078488137

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.69312385194829 
RMSE:	 6.057484944426053 
MAPE:	 4.755707959713801

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 61.47074835668693 
RMSE:	 7.8403283321992925 
MAPE:	 6.468176158698829

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 114.21230424130383 
RMSE:	 10.687015684525958 
MAPE:	 9.305044543155903

KAMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 21.57120658320832 
RMSE:	 4.6444813040002995 
MAPE:	 3.6837316829247877

MIDPOINT
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 17.38125304406819 
RMSE:	 4.169082997982673 
MAPE:	 3.3993243705608664

T3
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 60.321913944220896 
RMSE:	 7.766718351029661 
MAPE:	 6.200911576902634
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.38 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4352.703, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3889.412, Time=0.03 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.19 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3689.930, Time=0.04 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3574.245, Time=0.11 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.39 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.61 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3576.245, Time=0.23 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.021 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1783.123
Date:                Sun, 12 Dec 2021   AIC                           3574.245
Time:                        14:08:25   BIC                           3593.008
Sample:                             0   HQIC                          3581.451
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1480      0.004   -302.430      0.000      -1.155      -1.141
ar.L2         -0.8300      0.008    -99.682      0.000      -0.846      -0.814
ar.L3         -0.3687      0.007    -50.527      0.000      -0.383      -0.354
sigma2         4.9055      0.028    175.970      0.000       4.851       4.960
===================================================================================
Ljung-Box (L1) (Q):                  11.61   Jarque-Bera (JB):           1261976.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.16   Skew:                             2.52
Prob(H) (two-sided):                  0.00   Kurtosis:                       196.90
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05339, saving model to LSTM4.h5
90/90 - 5s - loss: 1.2628 - val_loss: 0.0534 - lr: 0.0010 - 5s/epoch - 56ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.9413 - val_loss: 0.0609 - lr: 0.0010 - 573ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.8281 - val_loss: 0.0685 - lr: 0.0010 - 551ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.7724 - val_loss: 0.0759 - lr: 0.0010 - 561ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.7358 - val_loss: 0.0833 - lr: 0.0010 - 554ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.7085 - val_loss: 0.0906 - lr: 0.0010 - 563ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6946 - val_loss: 0.0914 - lr: 1.0000e-04 - 569ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6925 - val_loss: 0.0922 - lr: 1.0000e-04 - 557ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6903 - val_loss: 0.0930 - lr: 1.0000e-04 - 570ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6881 - val_loss: 0.0938 - lr: 1.0000e-04 - 544ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6859 - val_loss: 0.0947 - lr: 1.0000e-04 - 563ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6845 - val_loss: 0.0948 - lr: 1.0000e-05 - 568ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6843 - val_loss: 0.0949 - lr: 1.0000e-05 - 552ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6840 - val_loss: 0.0950 - lr: 1.0000e-05 - 549ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6838 - val_loss: 0.0951 - lr: 1.0000e-05 - 549ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6835 - val_loss: 0.0952 - lr: 1.0000e-05 - 570ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6833 - val_loss: 0.0953 - lr: 1.0000e-05 - 560ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6830 - val_loss: 0.0954 - lr: 1.0000e-05 - 564ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6828 - val_loss: 0.0956 - lr: 1.0000e-05 - 549ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6825 - val_loss: 0.0957 - lr: 1.0000e-05 - 555ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6822 - val_loss: 0.0958 - lr: 1.0000e-05 - 547ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6820 - val_loss: 0.0959 - lr: 1.0000e-05 - 559ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6817 - val_loss: 0.0960 - lr: 1.0000e-05 - 563ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6814 - val_loss: 0.0962 - lr: 1.0000e-05 - 547ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6812 - val_loss: 0.0963 - lr: 1.0000e-05 - 551ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6809 - val_loss: 0.0964 - lr: 1.0000e-05 - 546ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6806 - val_loss: 0.0966 - lr: 1.0000e-05 - 551ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6803 - val_loss: 0.0967 - lr: 1.0000e-05 - 546ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6800 - val_loss: 0.0969 - lr: 1.0000e-05 - 548ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6798 - val_loss: 0.0970 - lr: 1.0000e-05 - 551ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6795 - val_loss: 0.0971 - lr: 1.0000e-05 - 548ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6792 - val_loss: 0.0973 - lr: 1.0000e-05 - 542ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6789 - val_loss: 0.0974 - lr: 1.0000e-05 - 541ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6786 - val_loss: 0.0976 - lr: 1.0000e-05 - 541ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6783 - val_loss: 0.0977 - lr: 1.0000e-05 - 541ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6780 - val_loss: 0.0979 - lr: 1.0000e-05 - 556ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6777 - val_loss: 0.0981 - lr: 1.0000e-05 - 552ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6774 - val_loss: 0.0982 - lr: 1.0000e-05 - 549ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6772 - val_loss: 0.0984 - lr: 1.0000e-05 - 563ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6769 - val_loss: 0.0985 - lr: 1.0000e-05 - 554ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6766 - val_loss: 0.0987 - lr: 1.0000e-05 - 559ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6763 - val_loss: 0.0989 - lr: 1.0000e-05 - 551ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6760 - val_loss: 0.0991 - lr: 1.0000e-05 - 562ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6757 - val_loss: 0.0992 - lr: 1.0000e-05 - 570ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6754 - val_loss: 0.0994 - lr: 1.0000e-05 - 549ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6751 - val_loss: 0.0996 - lr: 1.0000e-05 - 562ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6748 - val_loss: 0.0997 - lr: 1.0000e-05 - 559ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6745 - val_loss: 0.0999 - lr: 1.0000e-05 - 562ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6742 - val_loss: 0.1001 - lr: 1.0000e-05 - 564ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6739 - val_loss: 0.1003 - lr: 1.0000e-05 - 560ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05339
90/90 - 1s - loss: 0.6736 - val_loss: 0.1005 - lr: 1.0000e-05 - 548ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 22.0961825771905 
RMSE:	 4.700657674963207 
MAPE:	 3.7488296078488137

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.69312385194829 
RMSE:	 6.057484944426053 
MAPE:	 4.755707959713801

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 61.47074835668693 
RMSE:	 7.8403283321992925 
MAPE:	 6.468176158698829

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 114.21230424130383 
RMSE:	 10.687015684525958 
MAPE:	 9.305044543155903

KAMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 21.57120658320832 
RMSE:	 4.6444813040002995 
MAPE:	 3.6837316829247877

MIDPOINT
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 17.38125304406819 
RMSE:	 4.169082997982673 
MAPE:	 3.3993243705608664

T3
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 60.321913944220896 
RMSE:	 7.766718351029661 
MAPE:	 6.200911576902634

TEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 25.760985062606874 
RMSE:	 5.075528057513511 
MAPE:	 4.549137795705406
Runtime: mins: 11.88320966559999

Architecture Used

In [ ]:
from google.colab import files
import cv2
uploaded = files.upload()
Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to enable.
In [ ]:
img = cv2.imread('Experiment4.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)
Out[ ]:
<matplotlib.image.AxesImage at 0x7fb3f42846d0>

Model Plots

In [105]:
with open('simulation4_data.json') as json_file:
    simulation4 = json.load(json_file)
fileimg = 'Experiment4'
In [106]:
for i in range(len(list(simulation4.keys()))):
  SIM = list(simulation4.keys())[i]
  plot_train(simulation4,SIM)
  plot_test(simulation4,SIM)

----- Train RMSE for SMA ----- 2.261242280864947
----- Train_MSE_LSTM for SMA ----- 5.113216652771308
----- Train MAE LSTM for SMA ----- 2.2305949702121244

----- Test RMSE for SMA----- 4.700657674963207
----- Test_MSE_LSTM for SMA----- 22.0961825771905
----- Test_MAE_LSTM for SMA----- 3.7488296078488137

----- Train RMSE for EMA ----- 4.486578445228125
----- Train_MSE_LSTM for EMA ----- 20.12938614518562
----- Train MAE LSTM for EMA ----- 4.457049346206212

----- Test RMSE for EMA----- 6.057484944426053
----- Test_MSE_LSTM for EMA----- 36.69312385194829
----- Test_MAE_LSTM for EMA----- 4.755707959713801

----- Train RMSE for WMA ----- 3.9111937815761815
----- Train_MSE_LSTM for WMA ----- 15.29743679704019
----- Train MAE LSTM for WMA ----- 3.8069788630646055

----- Test RMSE for WMA----- 7.8403283321992925
----- Test_MSE_LSTM for WMA----- 61.47074835668693
----- Test_MAE_LSTM for WMA----- 6.468176158698829

----- Train RMSE for DEMA ----- 1.8914967024294371
----- Train_MSE_LSTM for DEMA ----- 3.577759775301435
----- Train MAE LSTM for DEMA ----- 1.0511807545576946

----- Test RMSE for DEMA----- 10.687015684525958
----- Test_MSE_LSTM for DEMA----- 114.21230424130383
----- Test_MAE_LSTM for DEMA----- 9.305044543155903

----- Train RMSE for KAMA ----- 0.6095271658293977
----- Train_MSE_LSTM for KAMA ----- 0.37152336588401813
----- Train MAE LSTM for KAMA ----- 0.1940257596497488

----- Test RMSE for KAMA----- 4.6444813040002995
----- Test_MSE_LSTM for KAMA----- 21.57120658320832
----- Test_MAE_LSTM for KAMA----- 3.6837316829247877

----- Train RMSE for MIDPOINT ----- 3.7511147201647144
----- Train_MSE_LSTM for MIDPOINT ----- 14.070861643836402
----- Train MAE LSTM for MIDPOINT ----- 3.721844446541059

----- Test RMSE for MIDPOINT----- 4.169082997982673
----- Test_MSE_LSTM for MIDPOINT----- 17.38125304406819
----- Test_MAE_LSTM for MIDPOINT----- 3.3993243705608664

----- Train RMSE for T3 ----- 2.13408676739365
----- Train_MSE_LSTM for T3 ----- 4.5543263307646775
----- Train MAE LSTM for T3 ----- 1.9476125499989727

----- Test RMSE for T3----- 7.766718351029661
----- Test_MSE_LSTM for T3----- 60.321913944220896
----- Test_MAE_LSTM for T3----- 6.200911576902634

----- Train RMSE for TEMA ----- 1.5059206544231611
----- Train_MSE_LSTM for TEMA ----- 2.267797017418282
----- Train MAE LSTM for TEMA ----- 1.3943178417659041

----- Test RMSE for TEMA----- 5.075528057513511
----- Test_MSE_LSTM for TEMA----- 25.760985062606874
----- Test_MAE_LSTM for TEMA----- 4.549137795705406

Arima w Exogenous Variable Multistep MutiVariate LSTM Hybrid Model Experiment 5

In [ ]:
def get_arima_exog(dataframe,original_data, train_len, test_len):    
    

    # prepare train and test data for exogenous vr
    X_value = pd.DataFrame(low_vol.iloc[:, :])
    y_value = pd.DataFrame(low_vol.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    X_scale_dataset = X_scaler.fit_transform(X_value)
    y_scale_dataset = y_scaler.fit_transform(y_value)
    # Get data and check shape
    # X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X_scale_dataset)
    y_train, y_test, = split_train_test(y_scale_dataset)
    yc_train,yc_test = split_train_test(low_vol_data)
    yc = yc_test.values.tolist()
    y_train_list = y_train.flatten().tolist()
    y_test_list = y_test.flatten().tolist()
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

    # Initialize model
    model = auto_arima(y_train_list,exogenous  = X_train,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
            suppress_warnings=True,stepwise=True,seasonal=True)

      # Determine model parameters
    print(model.summary())
    model.fit(y_train_list,maxiter=200)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

      # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
        model = pmdarima.ARIMA(order=order)
        model.fit(y_train_list)
        # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')

        prediction.append(model.predict()[0])
        y_train_list.append(y_test_list[i])

    predictionte = y_scaler.inverse_transform(np.array(prediction).reshape(-1,1))
    y_test_ = y_scaler.inverse_transform(np.array(y_test_list).reshape(-1,1))

    # Generate error data
    mse = mean_squared_error(yc_test, predictionte)
    rmse = mse ** 0.5
    mae = mean_absolute_error(y_test_ , predictionte )
    return yc,predictionte.flatten().tolist(), mse, rmse, mae
In [ ]:
def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    model = Sequential()
    model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    model.add(Dense(units=64,activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(units=output_dim))
    model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    ## Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM5.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()


    # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 3
    # define custom activation
    # 
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(input_dim, feature_size)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM5.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te
In [ ]:
if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation5 = {}
    imgfile = 'Experiment5'
    for ma in optimized_period:
                print(ma)
                print(functions[ma])
                print ( int( optimized_period[ma]))
              # if ma == 'SMA':
                low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
                low_vol = low_vol.fillna(0)
                low_vol_data = df['close']
                high_vol = pd.DataFrame()
                df2 = df.copy()
                for i in df2.columns:
                  if i in low_vol.columns:
                    high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
                high_vol_data = df['close']
                ## *****************************************************
                # Generate ARIMA and LSTM predictions
                print('\nWorking on ' + ma + ' predictions')
                try:
                  print('parameters used : ', train_len, test_len)
                  low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima_exog(low_vol,low_vol_data, train_len, test_len)
                except:
                    print('ARIMA error, skipping to next MA type')
                    continue
                Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
                final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
                mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
                rmse_ftr = mse_ftr ** 0.5
                mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
                mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

                final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
                mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
                rmse = mse ** 0.5
                mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                # Generate prediction accuracy
                actual = df['close'].tail(test_len).values
                result_1 = []
                result_2 = []
                for i in range(1, len(final_prediction)):
                    # Compare prediction to previous close price
                    if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                        result_1.append(1)
                    elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                        result_1.append(1)
                    else:
                        result_1.append(0)

                    # Compare prediction to previous prediction
                    if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                        result_2.append(1)
                    elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                        result_2.append(1)
                    else:
                        result_2.append(0)

                accuracy_1 = np.mean(result_1)
                accuracy_2 = np.mean(result_2)

                simulation5[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                              'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                  'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                              'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                  'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                              'rmse': rmse_ftr, 'mae' : mae_ftr},
                                  'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                            'rmse': rmse, 'mae': mae },
                                  'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

                # save simulation data here as checkpoint
                with open('simulation5_data.json', 'w') as fp:
                    json.dump(simulation5, fp)

                for ma in simulation5.keys():
                    print('\n' + ma)
                    print('Prediction vs Close:\t\t' + str(round(100*simulation5[ma]['accuracy']['prediction vs close'], 2))
                          + '% Accuracy')
                    print('Prediction vs Prediction:\t' + str(round(100*simulation5[ma]['accuracy']['prediction vs prediction'], 2))
                          + '% Accuracy')
                    print('MSE:\t', simulation5[ma]['final']['mse'],
                          '\nRMSE:\t', simulation5[ma]['final']['rmse'],
                          '\nMAPE:\t', simulation5[ma]['final']['mae'])#,
                          # '\nMAPE:\t', simulation[ma]['final']['mape'])
              # else:
              #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-14771.778, Time=16.11 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14135.387, Time=7.78 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15280.870, Time=12.96 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15393.475, Time=10.89 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-14981.217, Time=5.56 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14516.868, Time=17.01 sec
 ARIMA(0,3,1)(0,0,0)[0] intercept   : AIC=-15663.967, Time=12.26 sec
 ARIMA(0,3,0)(0,0,0)[0] intercept   : AIC=-13838.679, Time=6.48 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=-14734.479, Time=7.67 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-14866.409, Time=9.36 sec
 ARIMA(1,3,0)(0,0,0)[0] intercept   : AIC=-16157.403, Time=17.47 sec
 ARIMA(2,3,0)(0,0,0)[0] intercept   : AIC=-14855.623, Time=13.78 sec
 ARIMA(2,3,1)(0,0,0)[0] intercept   : AIC=-14720.644, Time=14.11 sec

Best model:  ARIMA(1,3,0)(0,0,0)[0] intercept
Total fit time: 151.496 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 0)   Log Likelihood                8103.701
Date:                Sun, 12 Dec 2021   AIC                         -16157.403
Time:                        14:24:44   BIC                         -16040.132
Sample:                             0   HQIC                        -16112.366
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
intercept  -2.802e-06   7.54e-07     -3.714      0.000   -4.28e-06   -1.32e-06
x1         -2.598e-05      0.001     -0.041      0.967      -0.001       0.001
x2         -2.599e-05      0.001     -0.047      0.963      -0.001       0.001
x3         -2.615e-05      0.001     -0.038      0.970      -0.001       0.001
x4             1.0000      0.001   1507.083      0.000       0.999       1.001
x5         -2.485e-05      0.001     -0.038      0.970      -0.001       0.001
x6         -2.807e-05   3.32e-05     -0.845      0.398   -9.32e-05    3.71e-05
x7         -2.593e-05   8.29e-05     -0.313      0.755      -0.000       0.000
x8             0.0019   7.15e-05     26.753      0.000       0.002       0.002
x9         -1.867e-06      0.001     -0.003      0.998      -0.001       0.001
x10            0.0003      0.000      0.644      0.520      -0.001       0.001
x11           -0.0025   8.93e-05    -28.145      0.000      -0.003      -0.002
x12            0.0015   8.06e-05     18.290      0.000       0.001       0.002
x13         -2.61e-05      0.000     -0.076      0.939      -0.001       0.001
x14        -7.719e-05      0.000     -0.374      0.708      -0.000       0.000
x15        -2.829e-05   8.57e-05     -0.330      0.741      -0.000       0.000
x16        -2.424e-05      0.000     -0.142      0.887      -0.000       0.000
x17        -2.292e-05   9.81e-05     -0.234      0.815      -0.000       0.000
x18         -4.39e-05      0.000     -0.429      0.668      -0.000       0.000
x19        -3.005e-05      0.000     -0.293      0.770      -0.000       0.000
x20         4.559e-05   9.36e-05      0.487      0.626      -0.000       0.000
x21        -7.981e-10      0.001  -9.88e-07      1.000      -0.002       0.002
x22        -1.557e-08      0.000     -0.000      1.000      -0.000       0.000
ar.L1         -0.6667   6.95e-05  -9587.073      0.000      -0.667      -0.667
sigma2      1.314e-10    7.8e-11      1.686      0.092   -2.14e-11    2.84e-10
===================================================================================
Ljung-Box (L1) (Q):                  90.59   Jarque-Bera (JB):           3138023.60
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.03   Skew:                             5.01
Prob(H) (two-sided):                  0.00   Kurtosis:                       308.71
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.36e+19. Standard errors may be unstable.
ARIMA order: (1, 3, 0) 

WARNING:tensorflow:Layer lstm_40 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_40 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.02955, saving model to LSTM5.h5
48/48 - 2s - loss: 0.2408 - val_loss: 0.0295 - lr: 0.0010 - 2s/epoch - 46ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0824 - val_loss: 0.0477 - lr: 0.0010 - 505ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0504 - val_loss: 0.4546 - lr: 0.0010 - 527ms/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0515 - val_loss: 0.0322 - lr: 0.0010 - 497ms/epoch - 10ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0495 - val_loss: 0.3863 - lr: 0.0010 - 521ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0330 - val_loss: 0.1281 - lr: 0.0010 - 470ms/epoch - 10ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0299 - val_loss: 0.1137 - lr: 1.0000e-04 - 527ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0330 - val_loss: 0.1029 - lr: 1.0000e-04 - 539ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0309 - val_loss: 0.1048 - lr: 1.0000e-04 - 537ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0310 - val_loss: 0.0998 - lr: 1.0000e-04 - 507ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0271 - val_loss: 0.0962 - lr: 1.0000e-04 - 501ms/epoch - 10ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0285 - val_loss: 0.0958 - lr: 1.0000e-05 - 495ms/epoch - 10ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0309 - val_loss: 0.0955 - lr: 1.0000e-05 - 531ms/epoch - 11ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0282 - val_loss: 0.0949 - lr: 1.0000e-05 - 473ms/epoch - 10ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0312 - val_loss: 0.0943 - lr: 1.0000e-05 - 530ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0329 - val_loss: 0.0938 - lr: 1.0000e-05 - 533ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0294 - val_loss: 0.0932 - lr: 1.0000e-05 - 524ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0304 - val_loss: 0.0928 - lr: 1.0000e-05 - 493ms/epoch - 10ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0272 - val_loss: 0.0922 - lr: 1.0000e-05 - 509ms/epoch - 11ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0290 - val_loss: 0.0917 - lr: 1.0000e-05 - 496ms/epoch - 10ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0293 - val_loss: 0.0910 - lr: 1.0000e-05 - 511ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0287 - val_loss: 0.0898 - lr: 1.0000e-05 - 540ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0302 - val_loss: 0.0893 - lr: 1.0000e-05 - 503ms/epoch - 10ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0291 - val_loss: 0.0888 - lr: 1.0000e-05 - 526ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0300 - val_loss: 0.0876 - lr: 1.0000e-05 - 495ms/epoch - 10ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0326 - val_loss: 0.0871 - lr: 1.0000e-05 - 522ms/epoch - 11ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0334 - val_loss: 0.0865 - lr: 1.0000e-05 - 497ms/epoch - 10ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0309 - val_loss: 0.0858 - lr: 1.0000e-05 - 504ms/epoch - 10ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0274 - val_loss: 0.0857 - lr: 1.0000e-05 - 485ms/epoch - 10ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0322 - val_loss: 0.0852 - lr: 1.0000e-05 - 499ms/epoch - 10ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0290 - val_loss: 0.0842 - lr: 1.0000e-05 - 540ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0274 - val_loss: 0.0830 - lr: 1.0000e-05 - 521ms/epoch - 11ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0287 - val_loss: 0.0832 - lr: 1.0000e-05 - 518ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0276 - val_loss: 0.0822 - lr: 1.0000e-05 - 529ms/epoch - 11ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0281 - val_loss: 0.0824 - lr: 1.0000e-05 - 477ms/epoch - 10ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0288 - val_loss: 0.0830 - lr: 1.0000e-05 - 529ms/epoch - 11ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0260 - val_loss: 0.0826 - lr: 1.0000e-05 - 505ms/epoch - 11ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0271 - val_loss: 0.0807 - lr: 1.0000e-05 - 509ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0278 - val_loss: 0.0789 - lr: 1.0000e-05 - 492ms/epoch - 10ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0272 - val_loss: 0.0792 - lr: 1.0000e-05 - 503ms/epoch - 10ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0278 - val_loss: 0.0799 - lr: 1.0000e-05 - 514ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0289 - val_loss: 0.0779 - lr: 1.0000e-05 - 544ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0302 - val_loss: 0.0769 - lr: 1.0000e-05 - 561ms/epoch - 12ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0271 - val_loss: 0.0764 - lr: 1.0000e-05 - 523ms/epoch - 11ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0277 - val_loss: 0.0761 - lr: 1.0000e-05 - 517ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0283 - val_loss: 0.0752 - lr: 1.0000e-05 - 513ms/epoch - 11ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0294 - val_loss: 0.0743 - lr: 1.0000e-05 - 483ms/epoch - 10ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0294 - val_loss: 0.0736 - lr: 1.0000e-05 - 508ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02955
48/48 - 1s - loss: 0.0289 - val_loss: 0.0722 - lr: 1.0000e-05 - 535ms/epoch - 11ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0263 - val_loss: 0.0722 - lr: 1.0000e-05 - 500ms/epoch - 10ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02955
48/48 - 0s - loss: 0.0268 - val_loss: 0.0715 - lr: 1.0000e-05 - 488ms/epoch - 10ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 36.387272258848725 
RMSE:	 6.032186358100081 
MAPE:	 4.990569235256131
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.831, Time=3.16 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=5.45 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16288.946, Time=9.11 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=7.78 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16226.419, Time=14.02 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-13742.844, Time=10.40 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16101.256, Time=25.43 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17006.489, Time=3.19 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17002.686, Time=4.21 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17086.654, Time=8.12 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=-16097.512, Time=20.97 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17002.132, Time=4.87 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-17004.011, Time=4.58 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 121.313 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8570.327
Date:                Sun, 12 Dec 2021   AIC                         -17086.654
Time:                        14:28:05   BIC                         -16960.001
Sample:                             0   HQIC                        -17038.014
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -2.333e-10   9.31e-21  -2.51e+10      0.000   -2.33e-10   -2.33e-10
x2         -2.326e-10   9.29e-21   -2.5e+10      0.000   -2.33e-10   -2.33e-10
x3         -2.342e-10   9.32e-21  -2.51e+10      0.000   -2.34e-10   -2.34e-10
x4             1.0000   9.31e-21   1.07e+20      0.000       1.000       1.000
x5         -2.121e-10   8.87e-21  -2.39e+10      0.000   -2.12e-10   -2.12e-10
x6         -8.055e-10   1.64e-20   -4.9e+10      0.000   -8.05e-10   -8.05e-10
x7         -2.312e-10   9.27e-21  -2.49e+10      0.000   -2.31e-10   -2.31e-10
x8          -2.26e-10   9.17e-21  -2.47e+10      0.000   -2.26e-10   -2.26e-10
x9         -1.174e-11   1.86e-21   -6.3e+09      0.000   -1.17e-11   -1.17e-11
x10        -4.486e-11   3.98e-21  -1.13e+10      0.000   -4.49e-11   -4.49e-11
x11        -2.235e-10   9.11e-21  -2.45e+10      0.000   -2.23e-10   -2.23e-10
x12         -2.28e-10   9.21e-21  -2.48e+10      0.000   -2.28e-10   -2.28e-10
x13        -2.332e-10   9.31e-21  -2.51e+10      0.000   -2.33e-10   -2.33e-10
x14         -1.78e-09   2.57e-20  -6.92e+10      0.000   -1.78e-09   -1.78e-09
x15        -2.118e-10   8.84e-21   -2.4e+10      0.000   -2.12e-10   -2.12e-10
x16         -5.28e-10    1.4e-20  -3.76e+10      0.000   -5.28e-10   -5.28e-10
x17        -2.173e-10   8.94e-21  -2.43e+10      0.000   -2.17e-10   -2.17e-10
x18         -3.83e-11   3.74e-21  -1.02e+10      0.000   -3.83e-11   -3.83e-11
x19        -2.606e-10   9.86e-21  -2.64e+10      0.000   -2.61e-10   -2.61e-10
x20        -2.433e-10   9.48e-21  -2.57e+10      0.000   -2.43e-10   -2.43e-10
x21        -3.774e-13   1.42e-24  -2.65e+11      0.000   -3.77e-13   -3.77e-13
x22        -1.096e-11   1.35e-24  -8.11e+12      0.000    -1.1e-11    -1.1e-11
ar.L1         -0.4919    1.5e-22  -3.27e+21      0.000      -0.492      -0.492
ar.L2         -0.1922   8.41e-23  -2.28e+21      0.000      -0.192      -0.192
ar.L3         -0.0462   4.01e-23  -1.15e+21      0.000      -0.046      -0.046
ma.L1         -0.7070   3.34e-22  -2.12e+21      0.000      -0.707      -0.707
sigma2      8.977e-11   6.95e-11      1.291      0.197   -4.65e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  54.80   Jarque-Bera (JB):           4212163.49
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.43
Prob(H) (two-sided):                  0.00   Kurtosis:                       357.21
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 1.65e+43. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

WARNING:tensorflow:Layer lstm_41 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_41 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.16777, saving model to LSTM5.h5
16/16 - 2s - loss: 0.2985 - val_loss: 0.1678 - lr: 0.0010 - 2s/epoch - 127ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.16777
16/16 - 0s - loss: 0.1674 - val_loss: 0.5109 - lr: 0.0010 - 194ms/epoch - 12ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.16777
16/16 - 0s - loss: 0.0656 - val_loss: 0.2042 - lr: 0.0010 - 193ms/epoch - 12ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.16777 to 0.02118, saving model to LSTM5.h5
16/16 - 0s - loss: 0.0593 - val_loss: 0.0212 - lr: 0.0010 - 244ms/epoch - 15ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.02118 to 0.00970, saving model to LSTM5.h5
16/16 - 0s - loss: 0.0429 - val_loss: 0.0097 - lr: 0.0010 - 244ms/epoch - 15ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0431 - val_loss: 0.0181 - lr: 0.0010 - 199ms/epoch - 12ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0322 - val_loss: 0.0147 - lr: 0.0010 - 207ms/epoch - 13ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0361 - val_loss: 0.0112 - lr: 0.0010 - 194ms/epoch - 12ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0360 - val_loss: 0.0945 - lr: 0.0010 - 180ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00010: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0300 - val_loss: 0.0127 - lr: 0.0010 - 197ms/epoch - 12ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0301 - val_loss: 0.0128 - lr: 1.0000e-04 - 211ms/epoch - 13ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0317 - val_loss: 0.0127 - lr: 1.0000e-04 - 201ms/epoch - 13ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0283 - val_loss: 0.0129 - lr: 1.0000e-04 - 211ms/epoch - 13ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0268 - val_loss: 0.0133 - lr: 1.0000e-04 - 196ms/epoch - 12ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00015: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0285 - val_loss: 0.0135 - lr: 1.0000e-04 - 212ms/epoch - 13ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0253 - val_loss: 0.0135 - lr: 1.0000e-05 - 192ms/epoch - 12ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0265 - val_loss: 0.0135 - lr: 1.0000e-05 - 185ms/epoch - 12ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0264 - val_loss: 0.0135 - lr: 1.0000e-05 - 196ms/epoch - 12ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0285 - val_loss: 0.0135 - lr: 1.0000e-05 - 188ms/epoch - 12ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00020: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0292 - val_loss: 0.0136 - lr: 1.0000e-05 - 211ms/epoch - 13ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0291 - val_loss: 0.0136 - lr: 1.0000e-05 - 207ms/epoch - 13ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0229 - val_loss: 0.0136 - lr: 1.0000e-05 - 190ms/epoch - 12ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0267 - val_loss: 0.0135 - lr: 1.0000e-05 - 211ms/epoch - 13ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0275 - val_loss: 0.0135 - lr: 1.0000e-05 - 191ms/epoch - 12ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0264 - val_loss: 0.0136 - lr: 1.0000e-05 - 190ms/epoch - 12ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0277 - val_loss: 0.0135 - lr: 1.0000e-05 - 192ms/epoch - 12ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0270 - val_loss: 0.0135 - lr: 1.0000e-05 - 197ms/epoch - 12ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0279 - val_loss: 0.0136 - lr: 1.0000e-05 - 195ms/epoch - 12ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0253 - val_loss: 0.0136 - lr: 1.0000e-05 - 183ms/epoch - 11ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0258 - val_loss: 0.0136 - lr: 1.0000e-05 - 198ms/epoch - 12ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0263 - val_loss: 0.0137 - lr: 1.0000e-05 - 194ms/epoch - 12ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0314 - val_loss: 0.0136 - lr: 1.0000e-05 - 191ms/epoch - 12ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0265 - val_loss: 0.0135 - lr: 1.0000e-05 - 214ms/epoch - 13ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0272 - val_loss: 0.0135 - lr: 1.0000e-05 - 214ms/epoch - 13ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0280 - val_loss: 0.0135 - lr: 1.0000e-05 - 194ms/epoch - 12ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0281 - val_loss: 0.0136 - lr: 1.0000e-05 - 200ms/epoch - 13ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0283 - val_loss: 0.0136 - lr: 1.0000e-05 - 190ms/epoch - 12ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0252 - val_loss: 0.0135 - lr: 1.0000e-05 - 193ms/epoch - 12ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0272 - val_loss: 0.0136 - lr: 1.0000e-05 - 194ms/epoch - 12ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0273 - val_loss: 0.0135 - lr: 1.0000e-05 - 206ms/epoch - 13ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0264 - val_loss: 0.0136 - lr: 1.0000e-05 - 190ms/epoch - 12ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0282 - val_loss: 0.0136 - lr: 1.0000e-05 - 186ms/epoch - 12ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0260 - val_loss: 0.0136 - lr: 1.0000e-05 - 215ms/epoch - 13ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0279 - val_loss: 0.0136 - lr: 1.0000e-05 - 180ms/epoch - 11ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0300 - val_loss: 0.0137 - lr: 1.0000e-05 - 203ms/epoch - 13ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0290 - val_loss: 0.0136 - lr: 1.0000e-05 - 187ms/epoch - 12ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0250 - val_loss: 0.0137 - lr: 1.0000e-05 - 180ms/epoch - 11ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0256 - val_loss: 0.0137 - lr: 1.0000e-05 - 193ms/epoch - 12ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0287 - val_loss: 0.0137 - lr: 1.0000e-05 - 192ms/epoch - 12ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0253 - val_loss: 0.0137 - lr: 1.0000e-05 - 205ms/epoch - 13ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0263 - val_loss: 0.0136 - lr: 1.0000e-05 - 201ms/epoch - 13ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0242 - val_loss: 0.0136 - lr: 1.0000e-05 - 190ms/epoch - 12ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0253 - val_loss: 0.0136 - lr: 1.0000e-05 - 192ms/epoch - 12ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0243 - val_loss: 0.0135 - lr: 1.0000e-05 - 203ms/epoch - 13ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00970
16/16 - 0s - loss: 0.0283 - val_loss: 0.0135 - lr: 1.0000e-05 - 198ms/epoch - 12ms/step
Epoch 00055: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 36.387272258848725 
RMSE:	 6.032186358100081 
MAPE:	 4.990569235256131

EMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 72.47565418845511 
RMSE:	 8.513263427643661 
MAPE:	 6.94585827976211
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16080.357, Time=14.46 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14973.799, Time=7.59 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15549.629, Time=2.20 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15317.999, Time=10.66 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16061.924, Time=11.81 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15376.406, Time=18.25 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16186.215, Time=4.40 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-15308.706, Time=15.25 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-14920.393, Time=15.78 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-16184.203, Time=3.61 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 104.037 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8118.107
Date:                Sun, 12 Dec 2021   AIC                         -16186.215
Time:                        14:39:07   BIC                         -16068.944
Sample:                             0   HQIC                        -16141.178
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -9.919e-15      0.000   -8.4e-11      1.000      -0.000       0.000
x2          3.194e-15    6.3e-05   5.07e-11      1.000      -0.000       0.000
x3          3.066e-15   7.71e-05   3.98e-11      1.000      -0.000       0.000
x4             1.0000    4.4e-05   2.27e+04      0.000       1.000       1.000
x5         -3.977e-15   4.68e-05  -8.49e-11      1.000   -9.18e-05    9.18e-05
x6         -5.906e-17   8.34e-05  -7.08e-13      1.000      -0.000       0.000
x7         -8.726e-15   7.85e-05  -1.11e-10      1.000      -0.000       0.000
x8             0.0014   4.94e-05     27.704      0.000       0.001       0.001
x9         -3.542e-15      0.001  -2.63e-12      1.000      -0.003       0.003
x10           -0.0012      0.001     -1.566      0.117      -0.003       0.000
x11            0.0052   3.01e-05    172.396      0.000       0.005       0.005
x12           -0.0065      0.000    -49.747      0.000      -0.007      -0.006
x13         1.963e-14   7.85e-05    2.5e-10      1.000      -0.000       0.000
x14        -2.134e-14      0.000  -1.01e-10      1.000      -0.000       0.000
x15         3.464e-12      0.000   2.92e-08      1.000      -0.000       0.000
x16        -7.174e-13   6.45e-05  -1.11e-08      1.000      -0.000       0.000
x17         2.537e-13   7.42e-05   3.42e-09      1.000      -0.000       0.000
x18        -2.964e-15      0.000  -7.78e-12      1.000      -0.001       0.001
x19        -3.613e-12   8.67e-05  -4.17e-08      1.000      -0.000       0.000
x20         6.244e-14      0.000    2.1e-10      1.000      -0.001       0.001
x21        -4.242e-16      0.000  -1.47e-12      1.000      -0.001       0.001
x22        -2.128e-15      0.001  -1.74e-12      1.000      -0.002       0.002
ma.L1         -1.3894   4.16e-05  -3.34e+04      0.000      -1.389      -1.389
ma.L2          0.4036      0.000   3637.465      0.000       0.403       0.404
sigma2      1.287e-10   7.27e-11      1.770      0.077   -1.38e-11    2.71e-10
===================================================================================
Ljung-Box (L1) (Q):                  69.00   Jarque-Bera (JB):           6269147.49
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            12.07
Prob(H) (two-sided):                  0.00   Kurtosis:                       434.65
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 6.47e+20. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

WARNING:tensorflow:Layer lstm_42 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_42 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.13812, saving model to LSTM5.h5
17/17 - 2s - loss: 0.5416 - val_loss: 0.1381 - lr: 0.0010 - 2s/epoch - 115ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.2008 - val_loss: 0.5647 - lr: 0.0010 - 187ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0776 - val_loss: 0.5295 - lr: 0.0010 - 193ms/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0543 - val_loss: 0.4118 - lr: 0.0010 - 196ms/epoch - 12ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0476 - val_loss: 0.1807 - lr: 0.0010 - 192ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0469 - val_loss: 0.1467 - lr: 0.0010 - 208ms/epoch - 12ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0326 - val_loss: 0.1473 - lr: 1.0000e-04 - 192ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0383 - val_loss: 0.1535 - lr: 1.0000e-04 - 188ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0362 - val_loss: 0.1557 - lr: 1.0000e-04 - 194ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0387 - val_loss: 0.1560 - lr: 1.0000e-04 - 215ms/epoch - 13ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0333 - val_loss: 0.1583 - lr: 1.0000e-04 - 204ms/epoch - 12ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0329 - val_loss: 0.1586 - lr: 1.0000e-05 - 209ms/epoch - 12ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0338 - val_loss: 0.1586 - lr: 1.0000e-05 - 200ms/epoch - 12ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0325 - val_loss: 0.1587 - lr: 1.0000e-05 - 211ms/epoch - 12ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0341 - val_loss: 0.1582 - lr: 1.0000e-05 - 216ms/epoch - 13ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0356 - val_loss: 0.1585 - lr: 1.0000e-05 - 189ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0332 - val_loss: 0.1588 - lr: 1.0000e-05 - 192ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0365 - val_loss: 0.1592 - lr: 1.0000e-05 - 202ms/epoch - 12ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0335 - val_loss: 0.1596 - lr: 1.0000e-05 - 209ms/epoch - 12ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0339 - val_loss: 0.1591 - lr: 1.0000e-05 - 227ms/epoch - 13ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0352 - val_loss: 0.1596 - lr: 1.0000e-05 - 211ms/epoch - 12ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0359 - val_loss: 0.1597 - lr: 1.0000e-05 - 194ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0328 - val_loss: 0.1594 - lr: 1.0000e-05 - 200ms/epoch - 12ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0355 - val_loss: 0.1591 - lr: 1.0000e-05 - 212ms/epoch - 12ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0323 - val_loss: 0.1589 - lr: 1.0000e-05 - 215ms/epoch - 13ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0323 - val_loss: 0.1594 - lr: 1.0000e-05 - 178ms/epoch - 10ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0372 - val_loss: 0.1595 - lr: 1.0000e-05 - 198ms/epoch - 12ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0329 - val_loss: 0.1600 - lr: 1.0000e-05 - 191ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0352 - val_loss: 0.1613 - lr: 1.0000e-05 - 204ms/epoch - 12ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0346 - val_loss: 0.1609 - lr: 1.0000e-05 - 199ms/epoch - 12ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0328 - val_loss: 0.1607 - lr: 1.0000e-05 - 213ms/epoch - 13ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0342 - val_loss: 0.1615 - lr: 1.0000e-05 - 208ms/epoch - 12ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0302 - val_loss: 0.1620 - lr: 1.0000e-05 - 221ms/epoch - 13ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0341 - val_loss: 0.1622 - lr: 1.0000e-05 - 201ms/epoch - 12ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0322 - val_loss: 0.1628 - lr: 1.0000e-05 - 204ms/epoch - 12ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0332 - val_loss: 0.1629 - lr: 1.0000e-05 - 220ms/epoch - 13ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0328 - val_loss: 0.1628 - lr: 1.0000e-05 - 202ms/epoch - 12ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0322 - val_loss: 0.1630 - lr: 1.0000e-05 - 200ms/epoch - 12ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0314 - val_loss: 0.1631 - lr: 1.0000e-05 - 198ms/epoch - 12ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0331 - val_loss: 0.1638 - lr: 1.0000e-05 - 209ms/epoch - 12ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0305 - val_loss: 0.1633 - lr: 1.0000e-05 - 190ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0351 - val_loss: 0.1630 - lr: 1.0000e-05 - 189ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0324 - val_loss: 0.1635 - lr: 1.0000e-05 - 201ms/epoch - 12ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0339 - val_loss: 0.1635 - lr: 1.0000e-05 - 218ms/epoch - 13ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0332 - val_loss: 0.1629 - lr: 1.0000e-05 - 198ms/epoch - 12ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0330 - val_loss: 0.1628 - lr: 1.0000e-05 - 210ms/epoch - 12ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0329 - val_loss: 0.1628 - lr: 1.0000e-05 - 212ms/epoch - 12ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0312 - val_loss: 0.1623 - lr: 1.0000e-05 - 188ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0348 - val_loss: 0.1622 - lr: 1.0000e-05 - 206ms/epoch - 12ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0295 - val_loss: 0.1621 - lr: 1.0000e-05 - 212ms/epoch - 12ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.13812
17/17 - 0s - loss: 0.0335 - val_loss: 0.1621 - lr: 1.0000e-05 - 205ms/epoch - 12ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 36.387272258848725 
RMSE:	 6.032186358100081 
MAPE:	 4.990569235256131

EMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 72.47565418845511 
RMSE:	 8.513263427643661 
MAPE:	 6.94585827976211

WMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 29.73090246364654 
RMSE:	 5.452605107987057 
MAPE:	 4.390044818690696
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.780, Time=3.04 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=5.38 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15584.877, Time=10.31 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=6.62 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15271.475, Time=10.32 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15128.422, Time=12.20 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16352.675, Time=22.43 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17028.022, Time=6.37 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17002.621, Time=3.84 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17085.445, Time=8.52 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=20.52 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17001.997, Time=4.47 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16996.668, Time=4.81 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 118.849 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.723
Date:                Sun, 12 Dec 2021   AIC                         -17085.445
Time:                        14:45:55   BIC                         -16958.792
Sample:                             0   HQIC                        -17036.805
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1           -2.8e-10   1.36e-20  -2.05e+10      0.000    -2.8e-10    -2.8e-10
x2         -2.817e-10   1.37e-20  -2.06e+10      0.000   -2.82e-10   -2.82e-10
x3         -2.805e-10   1.36e-20  -2.06e+10      0.000    -2.8e-10    -2.8e-10
x4             1.0000   1.37e-20   7.33e+19      0.000       1.000       1.000
x5         -2.598e-10   1.31e-20  -1.98e+10      0.000    -2.6e-10    -2.6e-10
x6         -1.389e-09   2.98e-20  -4.66e+10      0.000   -1.39e-09   -1.39e-09
x7         -2.789e-10   1.36e-20  -2.05e+10      0.000   -2.79e-10   -2.79e-10
x8         -2.761e-10   1.35e-20  -2.04e+10      0.000   -2.76e-10   -2.76e-10
x9         -2.219e-12   3.36e-22   -6.6e+09      0.000   -2.22e-12   -2.22e-12
x10        -1.345e-10   9.37e-21  -1.43e+10      0.000   -1.34e-10   -1.34e-10
x11        -2.899e-10   1.39e-20  -2.09e+10      0.000    -2.9e-10    -2.9e-10
x12        -2.602e-10   1.32e-20  -1.98e+10      0.000    -2.6e-10    -2.6e-10
x13        -2.807e-10   1.36e-20  -2.06e+10      0.000   -2.81e-10   -2.81e-10
x14         -1.87e-09   3.52e-20  -5.31e+10      0.000   -1.87e-09   -1.87e-09
x15        -2.825e-10   1.37e-20  -2.07e+10      0.000   -2.82e-10   -2.82e-10
x16        -8.187e-11   7.33e-21  -1.12e+10      0.000   -8.19e-11   -8.19e-11
x17        -2.441e-10   1.27e-20  -1.92e+10      0.000   -2.44e-10   -2.44e-10
x18        -6.411e-10   2.06e-20  -3.11e+10      0.000   -6.41e-10   -6.41e-10
x19        -2.929e-10   1.39e-20  -2.11e+10      0.000   -2.93e-10   -2.93e-10
x20        -4.339e-10    1.7e-20  -2.56e+10      0.000   -4.34e-10   -4.34e-10
x21        -3.589e-13   2.52e-24  -1.42e+11      0.000   -3.59e-13   -3.59e-13
x22        -1.088e-11   2.36e-24   -4.6e+12      0.000   -1.09e-11   -1.09e-11
ar.L1         -0.4923   1.46e-22  -3.37e+21      0.000      -0.492      -0.492
ar.L2         -0.1923   8.47e-23  -2.27e+21      0.000      -0.192      -0.192
ar.L3         -0.0462   4.02e-23  -1.15e+21      0.000      -0.046      -0.046
ma.L1         -0.7077   3.31e-22  -2.14e+21      0.000      -0.708      -0.708
sigma2       8.99e-11   6.95e-11      1.293      0.196   -4.64e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  55.15   Jarque-Bera (JB):           4171184.78
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.27
Prob(H) (two-sided):                  0.00   Kurtosis:                       355.49
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.53e+42. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

WARNING:tensorflow:Layer lstm_43 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_43 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.24371, saving model to LSTM5.h5
10/10 - 2s - loss: 1.3415 - val_loss: 0.2437 - lr: 0.0010 - 2s/epoch - 200ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.24371 to 0.11420, saving model to LSTM5.h5
10/10 - 0s - loss: 0.4349 - val_loss: 0.1142 - lr: 0.0010 - 148ms/epoch - 15ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.2272 - val_loss: 0.3306 - lr: 0.0010 - 123ms/epoch - 12ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0828 - val_loss: 0.5140 - lr: 0.0010 - 127ms/epoch - 13ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0789 - val_loss: 0.3226 - lr: 0.0010 - 130ms/epoch - 13ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0541 - val_loss: 0.2154 - lr: 0.0010 - 132ms/epoch - 13ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0511 - val_loss: 0.1715 - lr: 0.0010 - 131ms/epoch - 13ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0498 - val_loss: 0.1702 - lr: 1.0000e-04 - 128ms/epoch - 13ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0465 - val_loss: 0.1703 - lr: 1.0000e-04 - 146ms/epoch - 15ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0476 - val_loss: 0.1718 - lr: 1.0000e-04 - 132ms/epoch - 13ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0419 - val_loss: 0.1763 - lr: 1.0000e-04 - 124ms/epoch - 12ms/step
Epoch 12/500

Epoch 00012: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00012: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0431 - val_loss: 0.1837 - lr: 1.0000e-04 - 124ms/epoch - 12ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0405 - val_loss: 0.1839 - lr: 1.0000e-05 - 126ms/epoch - 13ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0442 - val_loss: 0.1847 - lr: 1.0000e-05 - 128ms/epoch - 13ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0491 - val_loss: 0.1855 - lr: 1.0000e-05 - 137ms/epoch - 14ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0434 - val_loss: 0.1861 - lr: 1.0000e-05 - 149ms/epoch - 15ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00017: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0469 - val_loss: 0.1874 - lr: 1.0000e-05 - 147ms/epoch - 15ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0456 - val_loss: 0.1892 - lr: 1.0000e-05 - 138ms/epoch - 14ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0406 - val_loss: 0.1902 - lr: 1.0000e-05 - 124ms/epoch - 12ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0434 - val_loss: 0.1905 - lr: 1.0000e-05 - 133ms/epoch - 13ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0408 - val_loss: 0.1909 - lr: 1.0000e-05 - 134ms/epoch - 13ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0437 - val_loss: 0.1909 - lr: 1.0000e-05 - 140ms/epoch - 14ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0436 - val_loss: 0.1914 - lr: 1.0000e-05 - 141ms/epoch - 14ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0439 - val_loss: 0.1913 - lr: 1.0000e-05 - 133ms/epoch - 13ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0431 - val_loss: 0.1909 - lr: 1.0000e-05 - 141ms/epoch - 14ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0499 - val_loss: 0.1903 - lr: 1.0000e-05 - 124ms/epoch - 12ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0433 - val_loss: 0.1895 - lr: 1.0000e-05 - 139ms/epoch - 14ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0468 - val_loss: 0.1892 - lr: 1.0000e-05 - 140ms/epoch - 14ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0407 - val_loss: 0.1896 - lr: 1.0000e-05 - 139ms/epoch - 14ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0413 - val_loss: 0.1895 - lr: 1.0000e-05 - 149ms/epoch - 15ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0423 - val_loss: 0.1895 - lr: 1.0000e-05 - 130ms/epoch - 13ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0417 - val_loss: 0.1891 - lr: 1.0000e-05 - 131ms/epoch - 13ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0391 - val_loss: 0.1891 - lr: 1.0000e-05 - 124ms/epoch - 12ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0418 - val_loss: 0.1895 - lr: 1.0000e-05 - 135ms/epoch - 13ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0438 - val_loss: 0.1901 - lr: 1.0000e-05 - 130ms/epoch - 13ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0410 - val_loss: 0.1909 - lr: 1.0000e-05 - 127ms/epoch - 13ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0427 - val_loss: 0.1914 - lr: 1.0000e-05 - 131ms/epoch - 13ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0421 - val_loss: 0.1918 - lr: 1.0000e-05 - 132ms/epoch - 13ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0440 - val_loss: 0.1921 - lr: 1.0000e-05 - 135ms/epoch - 13ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0382 - val_loss: 0.1928 - lr: 1.0000e-05 - 119ms/epoch - 12ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0442 - val_loss: 0.1934 - lr: 1.0000e-05 - 130ms/epoch - 13ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0389 - val_loss: 0.1937 - lr: 1.0000e-05 - 125ms/epoch - 12ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0418 - val_loss: 0.1939 - lr: 1.0000e-05 - 143ms/epoch - 14ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0408 - val_loss: 0.1939 - lr: 1.0000e-05 - 133ms/epoch - 13ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0430 - val_loss: 0.1941 - lr: 1.0000e-05 - 133ms/epoch - 13ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0409 - val_loss: 0.1952 - lr: 1.0000e-05 - 134ms/epoch - 13ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0438 - val_loss: 0.1953 - lr: 1.0000e-05 - 124ms/epoch - 12ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0396 - val_loss: 0.1964 - lr: 1.0000e-05 - 137ms/epoch - 14ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0412 - val_loss: 0.1969 - lr: 1.0000e-05 - 132ms/epoch - 13ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0425 - val_loss: 0.1967 - lr: 1.0000e-05 - 131ms/epoch - 13ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0406 - val_loss: 0.1960 - lr: 1.0000e-05 - 126ms/epoch - 13ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.11420
10/10 - 0s - loss: 0.0452 - val_loss: 0.1953 - lr: 1.0000e-05 - 130ms/epoch - 13ms/step
Epoch 00052: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 36.387272258848725 
RMSE:	 6.032186358100081 
MAPE:	 4.990569235256131

EMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 72.47565418845511 
RMSE:	 8.513263427643661 
MAPE:	 6.94585827976211

WMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 29.73090246364654 
RMSE:	 5.452605107987057 
MAPE:	 4.390044818690696

DEMA
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 39.142904723518775 
RMSE:	 6.256429071244936 
MAPE:	 4.920393911559133
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17059.325, Time=4.84 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=5.40 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16133.019, Time=7.50 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=7.17 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16091.980, Time=9.81 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16009.844, Time=14.86 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-15757.180, Time=11.57 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17029.439, Time=6.31 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17000.917, Time=4.91 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=45.027, Time=6.75 sec

Best model:  ARIMA(1,3,1)(0,0,0)[0]          
Total fit time: 79.127 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 1)   Log Likelihood                8554.662
Date:                Sun, 12 Dec 2021   AIC                         -17059.325
Time:                        14:57:02   BIC                         -16942.054
Sample:                             0   HQIC                        -17014.288
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -1.409e-10   5.52e-21  -2.55e+10      0.000   -1.41e-10   -1.41e-10
x2         -1.378e-10   5.47e-21  -2.52e+10      0.000   -1.38e-10   -1.38e-10
x3         -1.323e-10   5.35e-21  -2.47e+10      0.000   -1.32e-10   -1.32e-10
x4             1.0000   5.41e-21   1.85e+20      0.000       1.000       1.000
x5         -1.221e-10   5.15e-21  -2.37e+10      0.000   -1.22e-10   -1.22e-10
x6         -8.465e-10    1.3e-20  -6.53e+10      0.000   -8.47e-10   -8.47e-10
x7           -1.3e-10   5.32e-21  -2.44e+10      0.000    -1.3e-10    -1.3e-10
x8         -1.267e-10   5.27e-21  -2.41e+10      0.000   -1.27e-10   -1.27e-10
x9         -2.032e-11   6.67e-22  -3.05e+10      0.000   -2.03e-11   -2.03e-11
x10        -5.319e-11    2.3e-21  -2.31e+10      0.000   -5.32e-11   -5.32e-11
x11        -1.275e-10   5.28e-21  -2.42e+10      0.000   -1.28e-10   -1.28e-10
x12        -1.262e-10   5.23e-21  -2.41e+10      0.000   -1.26e-10   -1.26e-10
x13        -1.339e-10   5.39e-21  -2.49e+10      0.000   -1.34e-10   -1.34e-10
x14        -1.092e-09   1.55e-20  -7.06e+10      0.000   -1.09e-09   -1.09e-09
x15        -1.342e-10   5.42e-21  -2.48e+10      0.000   -1.34e-10   -1.34e-10
x16         -2.01e-10   6.63e-21  -3.03e+10      0.000   -2.01e-10   -2.01e-10
x17        -1.144e-10   5.01e-21  -2.29e+10      0.000   -1.14e-10   -1.14e-10
x18        -9.245e-11   4.49e-21  -2.06e+10      0.000   -9.24e-11   -9.24e-11
x19        -1.646e-10   6.01e-21  -2.74e+10      0.000   -1.65e-10   -1.65e-10
x20        -2.482e-10   7.35e-21  -3.37e+10      0.000   -2.48e-10   -2.48e-10
x21        -3.385e-12   3.14e-24  -1.08e+12      0.000   -3.39e-12   -3.39e-12
x22        -8.066e-11   2.47e-23  -3.26e+12      0.000   -8.07e-11   -8.07e-11
ar.L1         -0.2877   2.48e-22  -1.16e+21      0.000      -0.288      -0.288
ma.L1         -0.9134   1.05e-21   -8.7e+20      0.000      -0.913      -0.913
sigma2      9.332e-11   6.96e-11      1.340      0.180   -4.32e-11     2.3e-10
===================================================================================
Ljung-Box (L1) (Q):                  84.37   Jarque-Bera (JB):           4308764.36
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             5.22
Prob(H) (two-sided):                  0.00   Kurtosis:                       361.26
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.32e+42. Standard errors may be unstable.
ARIMA order: (1, 3, 1) 

WARNING:tensorflow:Layer lstm_44 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_44 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.28966, saving model to LSTM5.h5
45/45 - 2s - loss: 0.1649 - val_loss: 0.2897 - lr: 0.0010 - 2s/epoch - 52ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.28966 to 0.03060, saving model to LSTM5.h5
45/45 - 1s - loss: 0.0926 - val_loss: 0.0306 - lr: 0.0010 - 512ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0650 - val_loss: 0.5811 - lr: 0.0010 - 478ms/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0371 - val_loss: 0.1709 - lr: 0.0010 - 506ms/epoch - 11ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0399 - val_loss: 0.0468 - lr: 0.0010 - 481ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0357 - val_loss: 0.4813 - lr: 0.0010 - 474ms/epoch - 11ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0326 - val_loss: 0.3701 - lr: 0.0010 - 507ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0328 - val_loss: 0.3572 - lr: 1.0000e-04 - 472ms/epoch - 10ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0308 - val_loss: 0.3452 - lr: 1.0000e-04 - 456ms/epoch - 10ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0286 - val_loss: 0.3335 - lr: 1.0000e-04 - 473ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0278 - val_loss: 0.3212 - lr: 1.0000e-04 - 490ms/epoch - 11ms/step
Epoch 12/500

Epoch 00012: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00012: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0267 - val_loss: 0.3077 - lr: 1.0000e-04 - 480ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0282 - val_loss: 0.3065 - lr: 1.0000e-05 - 487ms/epoch - 11ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0261 - val_loss: 0.3053 - lr: 1.0000e-05 - 498ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0270 - val_loss: 0.3039 - lr: 1.0000e-05 - 499ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0288 - val_loss: 0.3025 - lr: 1.0000e-05 - 529ms/epoch - 12ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00017: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0274 - val_loss: 0.3012 - lr: 1.0000e-05 - 477ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0295 - val_loss: 0.2997 - lr: 1.0000e-05 - 496ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0262 - val_loss: 0.2985 - lr: 1.0000e-05 - 461ms/epoch - 10ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0265 - val_loss: 0.2971 - lr: 1.0000e-05 - 512ms/epoch - 11ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0295 - val_loss: 0.2956 - lr: 1.0000e-05 - 493ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0247 - val_loss: 0.2941 - lr: 1.0000e-05 - 508ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0259 - val_loss: 0.2925 - lr: 1.0000e-05 - 492ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0254 - val_loss: 0.2910 - lr: 1.0000e-05 - 525ms/epoch - 12ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0274 - val_loss: 0.2894 - lr: 1.0000e-05 - 502ms/epoch - 11ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0266 - val_loss: 0.2877 - lr: 1.0000e-05 - 500ms/epoch - 11ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0277 - val_loss: 0.2861 - lr: 1.0000e-05 - 494ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0274 - val_loss: 0.2846 - lr: 1.0000e-05 - 493ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0255 - val_loss: 0.2830 - lr: 1.0000e-05 - 522ms/epoch - 12ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0270 - val_loss: 0.2815 - lr: 1.0000e-05 - 476ms/epoch - 11ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0260 - val_loss: 0.2803 - lr: 1.0000e-05 - 536ms/epoch - 12ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0274 - val_loss: 0.2788 - lr: 1.0000e-05 - 513ms/epoch - 11ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0254 - val_loss: 0.2769 - lr: 1.0000e-05 - 492ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0282 - val_loss: 0.2754 - lr: 1.0000e-05 - 506ms/epoch - 11ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0261 - val_loss: 0.2735 - lr: 1.0000e-05 - 495ms/epoch - 11ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0254 - val_loss: 0.2720 - lr: 1.0000e-05 - 538ms/epoch - 12ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0262 - val_loss: 0.2705 - lr: 1.0000e-05 - 479ms/epoch - 11ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0242 - val_loss: 0.2690 - lr: 1.0000e-05 - 478ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0282 - val_loss: 0.2675 - lr: 1.0000e-05 - 470ms/epoch - 10ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0261 - val_loss: 0.2658 - lr: 1.0000e-05 - 500ms/epoch - 11ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0292 - val_loss: 0.2638 - lr: 1.0000e-05 - 522ms/epoch - 12ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0265 - val_loss: 0.2622 - lr: 1.0000e-05 - 510ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0257 - val_loss: 0.2604 - lr: 1.0000e-05 - 480ms/epoch - 11ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0250 - val_loss: 0.2586 - lr: 1.0000e-05 - 523ms/epoch - 12ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0266 - val_loss: 0.2568 - lr: 1.0000e-05 - 505ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0278 - val_loss: 0.2556 - lr: 1.0000e-05 - 493ms/epoch - 11ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03060
45/45 - 1s - loss: 0.0267 - val_loss: 0.2537 - lr: 1.0000e-05 - 503ms/epoch - 11ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0234 - val_loss: 0.2524 - lr: 1.0000e-05 - 491ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0244 - val_loss: 0.2504 - lr: 1.0000e-05 - 493ms/epoch - 11ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0262 - val_loss: 0.2494 - lr: 1.0000e-05 - 498ms/epoch - 11ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0262 - val_loss: 0.2482 - lr: 1.0000e-05 - 462ms/epoch - 10ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03060
45/45 - 0s - loss: 0.0273 - val_loss: 0.2466 - lr: 1.0000e-05 - 495ms/epoch - 11ms/step
Epoch 00052: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 36.387272258848725 
RMSE:	 6.032186358100081 
MAPE:	 4.990569235256131

EMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 72.47565418845511 
RMSE:	 8.513263427643661 
MAPE:	 6.94585827976211

WMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 29.73090246364654 
RMSE:	 5.452605107987057 
MAPE:	 4.390044818690696

DEMA
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 39.142904723518775 
RMSE:	 6.256429071244936 
MAPE:	 4.920393911559133

KAMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 52.56428057408519 
RMSE:	 7.25012279717283 
MAPE:	 6.170488218753182
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.733, Time=3.39 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.592, Time=5.41 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15587.551, Time=10.45 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.592, Time=7.47 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16365.334, Time=13.07 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16163.760, Time=16.61 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16245.181, Time=17.57 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17028.017, Time=6.11 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17106.133, Time=7.20 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17085.425, Time=8.11 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=-17000.553, Time=4.74 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 100.163 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood                8579.066
Date:                Sun, 12 Dec 2021   AIC                         -17106.133
Time:                        15:02:53   BIC                         -16984.171
Sample:                             0   HQIC                        -17059.294
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -3.048e-10   1.69e-20   -1.8e+10      0.000   -3.05e-10   -3.05e-10
x2         -3.042e-10   1.75e-20  -1.74e+10      0.000   -3.04e-10   -3.04e-10
x3         -3.108e-10   1.62e-20  -1.92e+10      0.000   -3.11e-10   -3.11e-10
x4             1.0000   1.69e-20   5.91e+19      0.000       1.000       1.000
x5         -2.767e-10   1.61e-20  -1.72e+10      0.000   -2.77e-10   -2.77e-10
x6         -6.072e-09   1.38e-19  -4.42e+10      0.000   -6.07e-09   -6.07e-09
x7           -2.8e-10   1.62e-20  -1.73e+10      0.000    -2.8e-10    -2.8e-10
x8         -2.792e-10   1.65e-20  -1.69e+10      0.000   -2.79e-10   -2.79e-10
x9         -1.502e-10   1.02e-21  -1.48e+11      0.000    -1.5e-10    -1.5e-10
x10        -2.482e-10    4.3e-21  -5.77e+10      0.000   -2.48e-10   -2.48e-10
x11        -2.764e-10   1.64e-20  -1.69e+10      0.000   -2.76e-10   -2.76e-10
x12        -2.857e-10   1.64e-20  -1.74e+10      0.000   -2.86e-10   -2.86e-10
x13        -2.944e-10   1.66e-20  -1.77e+10      0.000   -2.94e-10   -2.94e-10
x14        -2.403e-09   4.86e-20  -4.95e+10      0.000    -2.4e-09    -2.4e-09
x15        -3.368e-10   1.81e-20  -1.86e+10      0.000   -3.37e-10   -3.37e-10
x16        -2.169e-10   1.45e-20  -1.49e+10      0.000   -2.17e-10   -2.17e-10
x17        -2.124e-10   1.44e-20  -1.47e+10      0.000   -2.12e-10   -2.12e-10
x18        -9.125e-10   2.98e-20  -3.06e+10      0.000   -9.13e-10   -9.13e-10
x19        -3.698e-10    1.9e-20  -1.95e+10      0.000    -3.7e-10    -3.7e-10
x20          -8.9e-10   2.94e-20  -3.03e+10      0.000    -8.9e-10    -8.9e-10
x21        -1.844e-11   1.86e-22   -9.9e+10      0.000   -1.84e-11   -1.84e-11
x22        -2.169e-10   5.04e-22   -4.3e+11      0.000   -2.17e-10   -2.17e-10
ar.L1         -1.2011    7.4e-23  -1.62e+22      0.000      -1.201      -1.201
ar.L2         -0.9017   1.51e-22  -5.98e+21      0.000      -0.902      -0.902
ar.L3         -0.4014   9.48e-23  -4.23e+21      0.000      -0.401      -0.401
sigma2      8.782e-11   6.95e-11      1.264      0.206   -4.84e-11    2.24e-10
===================================================================================
Ljung-Box (L1) (Q):                   3.61   Jarque-Bera (JB):             16191.93
Prob(Q):                              0.06   Prob(JB):                         0.00
Heteroskedasticity (H):               0.35   Skew:                             0.59
Prob(H) (two-sided):                  0.00   Kurtosis:                        24.94
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 3.23e+40. Standard errors may be unstable.
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_45 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_45 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.01891, saving model to LSTM5.h5
58/58 - 3s - loss: 0.2885 - val_loss: 0.0189 - lr: 0.0010 - 3s/epoch - 44ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.1129 - val_loss: 0.0733 - lr: 0.0010 - 622ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0862 - val_loss: 0.1839 - lr: 0.0010 - 610ms/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0526 - val_loss: 0.0454 - lr: 0.0010 - 637ms/epoch - 11ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0452 - val_loss: 0.4101 - lr: 0.0010 - 627ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0457 - val_loss: 0.0734 - lr: 0.0010 - 614ms/epoch - 11ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0447 - val_loss: 0.0855 - lr: 1.0000e-04 - 621ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0383 - val_loss: 0.0801 - lr: 1.0000e-04 - 639ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0377 - val_loss: 0.0784 - lr: 1.0000e-04 - 617ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0338 - val_loss: 0.0625 - lr: 1.0000e-04 - 595ms/epoch - 10ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0363 - val_loss: 0.0497 - lr: 1.0000e-04 - 581ms/epoch - 10ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0331 - val_loss: 0.0519 - lr: 1.0000e-05 - 608ms/epoch - 10ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0333 - val_loss: 0.0530 - lr: 1.0000e-05 - 592ms/epoch - 10ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0340 - val_loss: 0.0522 - lr: 1.0000e-05 - 621ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0354 - val_loss: 0.0527 - lr: 1.0000e-05 - 637ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0309 - val_loss: 0.0551 - lr: 1.0000e-05 - 652ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0310 - val_loss: 0.0572 - lr: 1.0000e-05 - 614ms/epoch - 11ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0315 - val_loss: 0.0577 - lr: 1.0000e-05 - 614ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0366 - val_loss: 0.0579 - lr: 1.0000e-05 - 629ms/epoch - 11ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0348 - val_loss: 0.0588 - lr: 1.0000e-05 - 613ms/epoch - 11ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0325 - val_loss: 0.0590 - lr: 1.0000e-05 - 619ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0309 - val_loss: 0.0584 - lr: 1.0000e-05 - 658ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0318 - val_loss: 0.0586 - lr: 1.0000e-05 - 640ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0317 - val_loss: 0.0588 - lr: 1.0000e-05 - 621ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0302 - val_loss: 0.0597 - lr: 1.0000e-05 - 682ms/epoch - 12ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0324 - val_loss: 0.0613 - lr: 1.0000e-05 - 649ms/epoch - 11ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0312 - val_loss: 0.0613 - lr: 1.0000e-05 - 611ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0328 - val_loss: 0.0614 - lr: 1.0000e-05 - 632ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0339 - val_loss: 0.0612 - lr: 1.0000e-05 - 633ms/epoch - 11ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0338 - val_loss: 0.0603 - lr: 1.0000e-05 - 638ms/epoch - 11ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0337 - val_loss: 0.0609 - lr: 1.0000e-05 - 607ms/epoch - 10ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0293 - val_loss: 0.0599 - lr: 1.0000e-05 - 619ms/epoch - 11ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0300 - val_loss: 0.0599 - lr: 1.0000e-05 - 646ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0328 - val_loss: 0.0591 - lr: 1.0000e-05 - 654ms/epoch - 11ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0275 - val_loss: 0.0579 - lr: 1.0000e-05 - 629ms/epoch - 11ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0319 - val_loss: 0.0575 - lr: 1.0000e-05 - 667ms/epoch - 11ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0340 - val_loss: 0.0587 - lr: 1.0000e-05 - 623ms/epoch - 11ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0326 - val_loss: 0.0605 - lr: 1.0000e-05 - 601ms/epoch - 10ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0309 - val_loss: 0.0584 - lr: 1.0000e-05 - 633ms/epoch - 11ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0295 - val_loss: 0.0579 - lr: 1.0000e-05 - 620ms/epoch - 11ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0322 - val_loss: 0.0572 - lr: 1.0000e-05 - 611ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0304 - val_loss: 0.0562 - lr: 1.0000e-05 - 679ms/epoch - 12ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0285 - val_loss: 0.0564 - lr: 1.0000e-05 - 615ms/epoch - 11ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0334 - val_loss: 0.0541 - lr: 1.0000e-05 - 603ms/epoch - 10ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0321 - val_loss: 0.0528 - lr: 1.0000e-05 - 607ms/epoch - 10ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0305 - val_loss: 0.0519 - lr: 1.0000e-05 - 595ms/epoch - 10ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0317 - val_loss: 0.0536 - lr: 1.0000e-05 - 603ms/epoch - 10ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0308 - val_loss: 0.0556 - lr: 1.0000e-05 - 598ms/epoch - 10ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0276 - val_loss: 0.0571 - lr: 1.0000e-05 - 627ms/epoch - 11ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0326 - val_loss: 0.0556 - lr: 1.0000e-05 - 629ms/epoch - 11ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01891
58/58 - 1s - loss: 0.0283 - val_loss: 0.0543 - lr: 1.0000e-05 - 643ms/epoch - 11ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 36.387272258848725 
RMSE:	 6.032186358100081 
MAPE:	 4.990569235256131

EMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 72.47565418845511 
RMSE:	 8.513263427643661 
MAPE:	 6.94585827976211

WMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 29.73090246364654 
RMSE:	 5.452605107987057 
MAPE:	 4.390044818690696

DEMA
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 39.142904723518775 
RMSE:	 6.256429071244936 
MAPE:	 4.920393911559133

KAMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 52.56428057408519 
RMSE:	 7.25012279717283 
MAPE:	 6.170488218753182

MIDPOINT
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 44.21016710593271 
RMSE:	 6.649072650071791 
MAPE:	 5.476790088019583
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16954.347, Time=3.12 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14725.736, Time=3.16 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16732.390, Time=11.00 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15913.358, Time=9.36 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16550.077, Time=13.57 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15004.835, Time=12.29 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16027.273, Time=12.90 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-16934.995, Time=3.16 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16924.758, Time=4.73 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=-16952.347, Time=3.32 sec

Best model:  ARIMA(1,3,1)(0,0,0)[0]          
Total fit time: 76.633 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 1)   Log Likelihood                8502.173
Date:                Sun, 12 Dec 2021   AIC                         -16954.347
Time:                        15:06:52   BIC                         -16837.076
Sample:                             0   HQIC                        -16909.310
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1          3.409e-14   2.62e-06    1.3e-08      1.000   -5.13e-06    5.13e-06
x2          1.816e-14   2.62e-06   6.93e-09      1.000   -5.13e-06    5.13e-06
x3         -2.039e-15   2.47e-06  -8.26e-10      1.000   -4.84e-06    4.84e-06
x4             1.0000    2.5e-06      4e+05      0.000       1.000       1.000
x5          2.488e-12   2.48e-06      1e-06      1.000   -4.86e-06    4.86e-06
x6           2.84e-15   6.48e-06   4.38e-10      1.000   -1.27e-05    1.27e-05
x7          3.618e-13   3.24e-06   1.12e-07      1.000   -6.36e-06    6.36e-06
x8            -0.0002   4.44e-06    -43.079      0.000      -0.000      -0.000
x9           2.93e-14    6.3e-08   4.65e-07      1.000   -1.23e-07    1.23e-07
x10        -2.843e-05   9.63e-06     -2.951      0.003   -4.73e-05   -9.55e-06
x11            0.0002   3.28e-06     53.981      0.000       0.000       0.000
x12            0.0001   5.63e-06     23.078      0.000       0.000       0.000
x13        -2.595e-14   2.63e-06  -9.88e-09      1.000   -5.15e-06    5.15e-06
x14        -6.497e-14   5.76e-06  -1.13e-08      1.000   -1.13e-05    1.13e-05
x15         1.699e-12   3.08e-06   5.51e-07      1.000   -6.04e-06    6.04e-06
x16        -3.969e-12   4.77e-06  -8.33e-07      1.000   -9.34e-06    9.34e-06
x17         5.452e-12   8.58e-07   6.35e-06      1.000   -1.68e-06    1.68e-06
x18         -3.68e-13   1.33e-05  -2.76e-08      1.000   -2.61e-05    2.61e-05
x19        -5.643e-13   4.61e-06  -1.22e-07      1.000   -9.03e-06    9.03e-06
x20         6.651e-14    4.9e-05   1.36e-09      1.000   -9.61e-05    9.61e-05
x21         -1.76e-16   8.47e-11  -2.08e-06      1.000   -1.66e-10    1.66e-10
x22         -7.82e-16   1.75e-10  -4.47e-06      1.000   -3.43e-10    3.43e-10
ar.L1         -0.2858   5.46e-08  -5.24e+06      0.000      -0.286      -0.286
ma.L1         -0.9143   5.59e-08  -1.63e+07      0.000      -0.914      -0.914
sigma2          1e-10   6.99e-11      1.430      0.153   -3.71e-11    2.37e-10
===================================================================================
Ljung-Box (L1) (Q):                  84.00   Jarque-Bera (JB):           4822228.07
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            -6.05
Prob(H) (two-sided):                  0.00   Kurtosis:                       381.97
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 3.54e+27. Standard errors may be unstable.
ARIMA order: (1, 3, 1) 

WARNING:tensorflow:Layer lstm_46 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_46 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.03368, saving model to LSTM5.h5
43/43 - 3s - loss: 0.4064 - val_loss: 0.0337 - lr: 0.0010 - 3s/epoch - 65ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.03368
43/43 - 1s - loss: 0.1522 - val_loss: 0.3929 - lr: 0.0010 - 523ms/epoch - 12ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.03368
43/43 - 0s - loss: 0.0562 - val_loss: 0.4695 - lr: 0.0010 - 500ms/epoch - 12ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.03368
43/43 - 1s - loss: 0.0455 - val_loss: 0.0957 - lr: 0.0010 - 504ms/epoch - 12ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.03368 to 0.01773, saving model to LSTM5.h5
43/43 - 0s - loss: 0.0346 - val_loss: 0.0177 - lr: 0.0010 - 494ms/epoch - 11ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0339 - val_loss: 0.1766 - lr: 0.0010 - 473ms/epoch - 11ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0345 - val_loss: 0.0594 - lr: 0.0010 - 476ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0386 - val_loss: 0.0381 - lr: 0.0010 - 473ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0294 - val_loss: 0.0950 - lr: 0.0010 - 466ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00010: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0315 - val_loss: 0.0347 - lr: 0.0010 - 484ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0310 - val_loss: 0.0457 - lr: 1.0000e-04 - 450ms/epoch - 10ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0305 - val_loss: 0.0467 - lr: 1.0000e-04 - 481ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01773
43/43 - 1s - loss: 0.0283 - val_loss: 0.0472 - lr: 1.0000e-04 - 526ms/epoch - 12ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0307 - val_loss: 0.0463 - lr: 1.0000e-04 - 465ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00015: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0257 - val_loss: 0.0499 - lr: 1.0000e-04 - 465ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0256 - val_loss: 0.0496 - lr: 1.0000e-05 - 483ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0276 - val_loss: 0.0499 - lr: 1.0000e-05 - 451ms/epoch - 10ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0257 - val_loss: 0.0496 - lr: 1.0000e-05 - 490ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0317 - val_loss: 0.0502 - lr: 1.0000e-05 - 478ms/epoch - 11ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00020: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0263 - val_loss: 0.0502 - lr: 1.0000e-05 - 450ms/epoch - 10ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0268 - val_loss: 0.0502 - lr: 1.0000e-05 - 455ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0287 - val_loss: 0.0500 - lr: 1.0000e-05 - 457ms/epoch - 11ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0281 - val_loss: 0.0504 - lr: 1.0000e-05 - 458ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0257 - val_loss: 0.0505 - lr: 1.0000e-05 - 478ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01773
43/43 - 1s - loss: 0.0292 - val_loss: 0.0505 - lr: 1.0000e-05 - 501ms/epoch - 12ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0265 - val_loss: 0.0513 - lr: 1.0000e-05 - 497ms/epoch - 12ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0252 - val_loss: 0.0512 - lr: 1.0000e-05 - 460ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0280 - val_loss: 0.0518 - lr: 1.0000e-05 - 484ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0273 - val_loss: 0.0522 - lr: 1.0000e-05 - 471ms/epoch - 11ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0261 - val_loss: 0.0529 - lr: 1.0000e-05 - 495ms/epoch - 12ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01773
43/43 - 1s - loss: 0.0274 - val_loss: 0.0533 - lr: 1.0000e-05 - 508ms/epoch - 12ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0266 - val_loss: 0.0534 - lr: 1.0000e-05 - 464ms/epoch - 11ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0268 - val_loss: 0.0534 - lr: 1.0000e-05 - 494ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0278 - val_loss: 0.0538 - lr: 1.0000e-05 - 476ms/epoch - 11ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0278 - val_loss: 0.0537 - lr: 1.0000e-05 - 465ms/epoch - 11ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0244 - val_loss: 0.0530 - lr: 1.0000e-05 - 481ms/epoch - 11ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0280 - val_loss: 0.0535 - lr: 1.0000e-05 - 498ms/epoch - 12ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0261 - val_loss: 0.0538 - lr: 1.0000e-05 - 464ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0288 - val_loss: 0.0542 - lr: 1.0000e-05 - 462ms/epoch - 11ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0241 - val_loss: 0.0545 - lr: 1.0000e-05 - 451ms/epoch - 10ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0277 - val_loss: 0.0543 - lr: 1.0000e-05 - 454ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0261 - val_loss: 0.0541 - lr: 1.0000e-05 - 436ms/epoch - 10ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0245 - val_loss: 0.0541 - lr: 1.0000e-05 - 493ms/epoch - 11ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0261 - val_loss: 0.0545 - lr: 1.0000e-05 - 493ms/epoch - 11ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0261 - val_loss: 0.0531 - lr: 1.0000e-05 - 477ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0273 - val_loss: 0.0529 - lr: 1.0000e-05 - 453ms/epoch - 11ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0294 - val_loss: 0.0526 - lr: 1.0000e-05 - 471ms/epoch - 11ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0257 - val_loss: 0.0536 - lr: 1.0000e-05 - 470ms/epoch - 11ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0296 - val_loss: 0.0539 - lr: 1.0000e-05 - 473ms/epoch - 11ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0292 - val_loss: 0.0538 - lr: 1.0000e-05 - 487ms/epoch - 11ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0294 - val_loss: 0.0543 - lr: 1.0000e-05 - 470ms/epoch - 11ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0251 - val_loss: 0.0552 - lr: 1.0000e-05 - 455ms/epoch - 11ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01773
43/43 - 1s - loss: 0.0264 - val_loss: 0.0555 - lr: 1.0000e-05 - 501ms/epoch - 12ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0279 - val_loss: 0.0551 - lr: 1.0000e-05 - 468ms/epoch - 11ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01773
43/43 - 0s - loss: 0.0265 - val_loss: 0.0544 - lr: 1.0000e-05 - 448ms/epoch - 10ms/step
Epoch 00055: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 36.387272258848725 
RMSE:	 6.032186358100081 
MAPE:	 4.990569235256131

EMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 72.47565418845511 
RMSE:	 8.513263427643661 
MAPE:	 6.94585827976211

WMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 29.73090246364654 
RMSE:	 5.452605107987057 
MAPE:	 4.390044818690696

DEMA
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 39.142904723518775 
RMSE:	 6.256429071244936 
MAPE:	 4.920393911559133

KAMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 52.56428057408519 
RMSE:	 7.25012279717283 
MAPE:	 6.170488218753182

MIDPOINT
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 44.21016710593271 
RMSE:	 6.649072650071791 
MAPE:	 5.476790088019583

T3
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 64.94642382025489 
RMSE:	 8.058934409725326 
MAPE:	 6.415762745110697
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16412.930, Time=13.44 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14867.265, Time=8.15 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15902.803, Time=6.80 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15117.003, Time=9.36 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15669.652, Time=9.45 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-12676.374, Time=11.44 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16418.724, Time=11.14 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-15107.772, Time=19.42 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15708.742, Time=22.37 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-13418.641, Time=28.39 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 139.987 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8234.362
Date:                Sun, 12 Dec 2021   AIC                         -16418.724
Time:                        15:13:15   BIC                         -16301.453
Sample:                             0   HQIC                        -16373.687
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -1.784e-07      0.001     -0.000      1.000      -0.002       0.002
x2         -1.784e-07      0.001     -0.000      1.000      -0.003       0.003
x3         -1.794e-07      0.001     -0.000      1.000      -0.002       0.002
x4             1.0000      0.000   2616.546      0.000       0.999       1.001
x5         -1.704e-07      0.000     -0.000      1.000      -0.001       0.001
x6         -2.858e-07   3.31e-05     -0.009      0.993   -6.52e-05    6.46e-05
x7         -1.754e-07      0.001     -0.000      1.000      -0.002       0.002
x8             0.0007      0.000      3.091      0.002       0.000       0.001
x9          3.313e-08      0.000   9.39e-05      1.000      -0.001       0.001
x10         3.499e-06      0.000      0.022      0.983      -0.000       0.000
x11           -0.0003      0.000     -1.284      0.199      -0.001       0.000
x12        -6.362e-05      0.000     -0.260      0.795      -0.001       0.000
x13        -1.783e-07      0.000     -0.001      0.999      -0.000       0.000
x14        -5.244e-07      0.001     -0.001      0.999      -0.001       0.001
x15        -1.737e-07      0.000     -0.001      0.999      -0.000       0.000
x16        -2.583e-07      0.000     -0.001      0.999      -0.000       0.000
x17         -1.74e-07      0.000     -0.001      0.999      -0.000       0.000
x18        -5.776e-08      0.000     -0.000      1.000      -0.000       0.000
x19         -1.95e-07      0.000     -0.002      0.999      -0.000       0.000
x20          1.72e-07      0.000      0.001      0.999      -0.000       0.000
x21        -7.548e-10      0.001  -9.93e-07      1.000      -0.001       0.001
x22        -1.194e-08      0.000  -8.47e-05      1.000      -0.000       0.000
ma.L1         -1.3862   1.58e-05  -8.78e+04      0.000      -1.386      -1.386
ma.L2          0.4019   4.28e-05   9396.834      0.000       0.402       0.402
sigma2      1.265e-10   7.58e-11      1.669      0.095    -2.2e-11    2.75e-10
===================================================================================
Ljung-Box (L1) (Q):                  66.79   Jarque-Bera (JB):           5900482.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                           -11.32
Prob(H) (two-sided):                  0.00   Kurtosis:                       421.81
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.07e+19. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

WARNING:tensorflow:Layer lstm_47 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_47 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.07083, saving model to LSTM5.h5
90/90 - 3s - loss: 0.1074 - val_loss: 0.0708 - lr: 0.0010 - 3s/epoch - 32ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.07083
90/90 - 1s - loss: 0.0851 - val_loss: 0.2284 - lr: 0.0010 - 938ms/epoch - 10ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.07083
90/90 - 1s - loss: 0.0725 - val_loss: 1.2299 - lr: 0.0010 - 975ms/epoch - 11ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.07083
90/90 - 1s - loss: 0.0495 - val_loss: 0.5107 - lr: 0.0010 - 969ms/epoch - 11ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.07083
90/90 - 1s - loss: 0.0374 - val_loss: 0.2034 - lr: 0.0010 - 922ms/epoch - 10ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.07083 to 0.02678, saving model to LSTM5.h5
90/90 - 1s - loss: 0.0358 - val_loss: 0.0268 - lr: 0.0010 - 968ms/epoch - 11ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0717 - val_loss: 0.0848 - lr: 0.0010 - 882ms/epoch - 10ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0303 - val_loss: 0.0579 - lr: 0.0010 - 982ms/epoch - 11ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0315 - val_loss: 0.5213 - lr: 0.0010 - 984ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0323 - val_loss: 0.2960 - lr: 0.0010 - 903ms/epoch - 10ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0264 - val_loss: 0.1208 - lr: 0.0010 - 907ms/epoch - 10ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0248 - val_loss: 0.1148 - lr: 1.0000e-04 - 970ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0228 - val_loss: 0.1041 - lr: 1.0000e-04 - 903ms/epoch - 10ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0227 - val_loss: 0.1045 - lr: 1.0000e-04 - 901ms/epoch - 10ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0251 - val_loss: 0.1029 - lr: 1.0000e-04 - 970ms/epoch - 11ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0229 - val_loss: 0.1019 - lr: 1.0000e-04 - 946ms/epoch - 11ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0226 - val_loss: 0.1016 - lr: 1.0000e-05 - 938ms/epoch - 10ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0234 - val_loss: 0.1021 - lr: 1.0000e-05 - 948ms/epoch - 11ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0212 - val_loss: 0.1024 - lr: 1.0000e-05 - 909ms/epoch - 10ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0238 - val_loss: 0.1005 - lr: 1.0000e-05 - 955ms/epoch - 11ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0235 - val_loss: 0.1004 - lr: 1.0000e-05 - 934ms/epoch - 10ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0229 - val_loss: 0.1012 - lr: 1.0000e-05 - 918ms/epoch - 10ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0217 - val_loss: 0.1007 - lr: 1.0000e-05 - 954ms/epoch - 11ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0201 - val_loss: 0.0996 - lr: 1.0000e-05 - 969ms/epoch - 11ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0220 - val_loss: 0.0993 - lr: 1.0000e-05 - 960ms/epoch - 11ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0229 - val_loss: 0.0995 - lr: 1.0000e-05 - 941ms/epoch - 10ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0210 - val_loss: 0.0994 - lr: 1.0000e-05 - 957ms/epoch - 11ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0237 - val_loss: 0.0990 - lr: 1.0000e-05 - 938ms/epoch - 10ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0218 - val_loss: 0.0973 - lr: 1.0000e-05 - 929ms/epoch - 10ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0243 - val_loss: 0.0971 - lr: 1.0000e-05 - 894ms/epoch - 10ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0231 - val_loss: 0.0976 - lr: 1.0000e-05 - 922ms/epoch - 10ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0234 - val_loss: 0.0994 - lr: 1.0000e-05 - 902ms/epoch - 10ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0220 - val_loss: 0.0994 - lr: 1.0000e-05 - 931ms/epoch - 10ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0206 - val_loss: 0.0983 - lr: 1.0000e-05 - 945ms/epoch - 11ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0231 - val_loss: 0.0971 - lr: 1.0000e-05 - 911ms/epoch - 10ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0223 - val_loss: 0.0985 - lr: 1.0000e-05 - 905ms/epoch - 10ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0201 - val_loss: 0.0993 - lr: 1.0000e-05 - 919ms/epoch - 10ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0212 - val_loss: 0.0992 - lr: 1.0000e-05 - 965ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0211 - val_loss: 0.0995 - lr: 1.0000e-05 - 994ms/epoch - 11ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0212 - val_loss: 0.0989 - lr: 1.0000e-05 - 986ms/epoch - 11ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0246 - val_loss: 0.0985 - lr: 1.0000e-05 - 963ms/epoch - 11ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0228 - val_loss: 0.0986 - lr: 1.0000e-05 - 952ms/epoch - 11ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0226 - val_loss: 0.0978 - lr: 1.0000e-05 - 880ms/epoch - 10ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0220 - val_loss: 0.0978 - lr: 1.0000e-05 - 923ms/epoch - 10ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0216 - val_loss: 0.0987 - lr: 1.0000e-05 - 929ms/epoch - 10ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0210 - val_loss: 0.1003 - lr: 1.0000e-05 - 920ms/epoch - 10ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0215 - val_loss: 0.1010 - lr: 1.0000e-05 - 915ms/epoch - 10ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0238 - val_loss: 0.1011 - lr: 1.0000e-05 - 911ms/epoch - 10ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0224 - val_loss: 0.1010 - lr: 1.0000e-05 - 944ms/epoch - 10ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0252 - val_loss: 0.1000 - lr: 1.0000e-05 - 922ms/epoch - 10ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0199 - val_loss: 0.1015 - lr: 1.0000e-05 - 964ms/epoch - 11ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0222 - val_loss: 0.1016 - lr: 1.0000e-05 - 970ms/epoch - 11ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0215 - val_loss: 0.0989 - lr: 1.0000e-05 - 962ms/epoch - 11ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0218 - val_loss: 0.1016 - lr: 1.0000e-05 - 936ms/epoch - 10ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0226 - val_loss: 0.1009 - lr: 1.0000e-05 - 901ms/epoch - 10ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.02678
90/90 - 1s - loss: 0.0231 - val_loss: 0.0999 - lr: 1.0000e-05 - 974ms/epoch - 11ms/step
Epoch 00056: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	50.75% Accuracy
MSE:	 36.387272258848725 
RMSE:	 6.032186358100081 
MAPE:	 4.990569235256131

EMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 72.47565418845511 
RMSE:	 8.513263427643661 
MAPE:	 6.94585827976211

WMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 29.73090246364654 
RMSE:	 5.452605107987057 
MAPE:	 4.390044818690696

DEMA
Prediction vs Close:		50.37% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 39.142904723518775 
RMSE:	 6.256429071244936 
MAPE:	 4.920393911559133

KAMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 52.56428057408519 
RMSE:	 7.25012279717283 
MAPE:	 6.170488218753182

MIDPOINT
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 44.21016710593271 
RMSE:	 6.649072650071791 
MAPE:	 5.476790088019583

T3
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 64.94642382025489 
RMSE:	 8.058934409725326 
MAPE:	 6.415762745110697

TEMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 29.21500753639505 
RMSE:	 5.4050908906691895 
MAPE:	 4.44965723634719
Runtime: mins: 56.502691550266654

Architecture Used

In [ ]:
from google.colab import files
import cv2
uploaded = files.upload()
Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to enable.
In [ ]:
img = cv2.imread('Experiment5.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)
Out[ ]:
<matplotlib.image.AxesImage at 0x7fb48eb72350>

Model Plots

In [107]:
with open('simulation5_data.json') as json_file:
    simulation5 = json.load(json_file)
fileimg = 'Experiment5'
In [108]:
for i in range(len(list(simulation5.keys()))):
  SIM = list(simulation5.keys())[i]
  plot_train(simulation5,SIM)
  plot_test(simulation5,SIM)

----- Train RMSE for SMA ----- 7.896795928299453
----- Train_MSE_LSTM for SMA ----- 62.35938593320682
----- Train MAE LSTM for SMA ----- 6.857639569537322

----- Test RMSE for SMA----- 6.032186358100081
----- Test_MSE_LSTM for SMA----- 36.387272258848725
----- Test_MAE_LSTM for SMA----- 4.990569235256131

----- Train RMSE for EMA ----- 9.362436614173118
----- Train_MSE_LSTM for EMA ----- 87.65521935440941
----- Train MAE LSTM for EMA ----- 8.20909698434303

----- Test RMSE for EMA----- 8.513263427643661
----- Test_MSE_LSTM for EMA----- 72.47565418845511
----- Test_MAE_LSTM for EMA----- 6.94585827976211

----- Train RMSE for WMA ----- 9.66038426972872
----- Train_MSE_LSTM for WMA ----- 93.3230242388221
----- Train MAE LSTM for WMA ----- 8.543432257543918

----- Test RMSE for WMA----- 5.452605107987057
----- Test_MSE_LSTM for WMA----- 29.73090246364654
----- Test_MAE_LSTM for WMA----- 4.390044818690696

----- Train RMSE for DEMA ----- 10.778650785623652
----- Train_MSE_LSTM for DEMA ----- 116.17931275842537
----- Train MAE LSTM for DEMA ----- 9.483069223000225

----- Test RMSE for DEMA----- 6.256429071244936
----- Test_MSE_LSTM for DEMA----- 39.142904723518775
----- Test_MAE_LSTM for DEMA----- 4.920393911559133

----- Train RMSE for KAMA ----- 9.224758606883512
----- Train_MSE_LSTM for KAMA ----- 85.09617135527144
----- Train MAE LSTM for KAMA ----- 8.391264192349656

----- Test RMSE for KAMA----- 7.25012279717283
----- Test_MSE_LSTM for KAMA----- 52.56428057408519
----- Test_MAE_LSTM for KAMA----- 6.170488218753182

----- Train RMSE for MIDPOINT ----- 8.415583524174332
----- Train_MSE_LSTM for MIDPOINT ----- 70.82204605235448
----- Train MAE LSTM for MIDPOINT ----- 7.418297143134353

----- Test RMSE for MIDPOINT----- 6.649072650071791
----- Test_MSE_LSTM for MIDPOINT----- 44.21016710593271
----- Test_MAE_LSTM for MIDPOINT----- 5.476790088019583

----- Train RMSE for T3 ----- 10.972513364419068
----- Train_MSE_LSTM for T3 ----- 120.39604953235508
----- Train MAE LSTM for T3 ----- 9.852330220934686

----- Test RMSE for T3----- 8.058934409725326
----- Test_MSE_LSTM for T3----- 64.94642382025489
----- Test_MAE_LSTM for T3----- 6.415762745110697

----- Train RMSE for TEMA ----- 6.651107172535585
----- Train_MSE_LSTM for TEMA ----- 44.237226620554296
----- Train MAE LSTM for TEMA ----- 4.542467270827089

----- Test RMSE for TEMA----- 5.4050908906691895
----- Test_MSE_LSTM for TEMA----- 29.21500753639505
----- Test_MAE_LSTM for TEMA----- 4.44965723634719

Arima w Exogenous Variable Multistep MutiVariate LSTM Hybrid Model Experiment 6

In [ ]:
def get_arima_exog(dataframe,original_data, train_len, test_len):    
    

    # prepare train and test data for exogenous vr
    X_value = pd.DataFrame(low_vol.iloc[:, :])
    y_value = pd.DataFrame(low_vol.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    X_scale_dataset = X_scaler.fit_transform(X_value)
    y_scale_dataset = y_scaler.fit_transform(y_value)
    # Get data and check shape
    # X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X_scale_dataset)
    y_train, y_test, = split_train_test(y_scale_dataset)
    yc_train,yc_test = split_train_test(low_vol_data)
    yc = yc_test.values.tolist()
    y_train_list = y_train.flatten().tolist()
    y_test_list = y_test.flatten().tolist()
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

    # Initialize model
    model = auto_arima(y_train_list,exogenous  = X_train,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
            suppress_warnings=True,stepwise=True,seasonal=True)

      # Determine model parameters
    print(model.summary())
    model.fit(y_train_list,maxiter=200)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

      # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
        model = pmdarima.ARIMA(order=order)
        model.fit(y_train_list)
        # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')

        prediction.append(model.predict()[0])
        y_train_list.append(y_test_list[i])

    predictionte = y_scaler.inverse_transform(np.array(prediction).reshape(-1,1))
    y_test_ = y_scaler.inverse_transform(np.array(y_test_list).reshape(-1,1))

    # Generate error data
    mse = mean_squared_error(yc_test, predictionte)
    rmse = mse ** 0.5
    mae = mean_absolute_error(y_test_ , predictionte )
    return yc,predictionte.flatten().tolist(), mse, rmse, mae
In [ ]:
def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det =20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()


    # # option 2
    model = Sequential()
    model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    model.add(Dense(64))
    model.add(Dense(units=output_dim))
    model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM6.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()

    # Option 3
    # define custom activation
    # 
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te
In [ ]:
if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation6 = {}
    imgfile = 'Experiment6'
    for ma in optimized_period:
                print(ma)
                print(functions[ma])
                print ( int( optimized_period[ma]))
              # if ma == 'SMA':
                low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
                low_vol = low_vol.fillna(0)
                low_vol_data = df['close']
                high_vol = pd.DataFrame()
                df2 = df.copy()
                for i in df2.columns:
                  if i in low_vol.columns:
                    high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
                high_vol_data = df['close']
                ## *****************************************************
                # Generate ARIMA and LSTM predictions
                print('\nWorking on ' + ma + ' predictions')
                try:
                  print('parameters used : ', train_len, test_len)
                  low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima_exog(low_vol,low_vol_data, train_len, test_len)
                except:
                    print('ARIMA error, skipping to next MA type')
                    continue
                Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
                final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
                mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
                rmse_ftr = mse_ftr ** 0.5
                mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
                mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

                final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
                mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
                rmse = mse ** 0.5
                mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                # Generate prediction accuracy
                actual = df['close'].tail(test_len).values
                result_1 = []
                result_2 = []
                for i in range(1, len(final_prediction)):
                    # Compare prediction to previous close price
                    if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                        result_1.append(1)
                    elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                        result_1.append(1)
                    else:
                        result_1.append(0)

                    # Compare prediction to previous prediction
                    if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                        result_2.append(1)
                    elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                        result_2.append(1)
                    else:
                        result_2.append(0)

                accuracy_1 = np.mean(result_1)
                accuracy_2 = np.mean(result_2)

                simulation6[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                              'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                  'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                              'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                  'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                              'rmse': rmse_ftr, 'mae' : mae_ftr},
                                  'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                            'rmse': rmse, 'mae': mae },
                                  'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

                # save simulation data here as checkpoint
                with open('simulation6_data.json', 'w') as fp:
                    json.dump(simulation6, fp)

                for ma in simulation6.keys():
                    print('\n' + ma)
                    print('Prediction vs Close:\t\t' + str(round(100*simulation6[ma]['accuracy']['prediction vs close'], 2))
                          + '% Accuracy')
                    print('Prediction vs Prediction:\t' + str(round(100*simulation6[ma]['accuracy']['prediction vs prediction'], 2))
                          + '% Accuracy')
                    print('MSE:\t', simulation6[ma]['final']['mse'],
                          '\nRMSE:\t', simulation6[ma]['final']['rmse'],
                          '\nMAPE:\t', simulation6[ma]['final']['mae'])#,
                          # '\nMAPE:\t', simulation[ma]['final']['mape'])
              # else:
              #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-14771.778, Time=13.25 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14135.387, Time=6.10 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15280.870, Time=10.58 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15393.475, Time=9.00 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-14981.217, Time=4.97 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14516.868, Time=13.91 sec
 ARIMA(0,3,1)(0,0,0)[0] intercept   : AIC=-15663.967, Time=10.04 sec
 ARIMA(0,3,0)(0,0,0)[0] intercept   : AIC=-13838.679, Time=5.35 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=-14734.479, Time=6.37 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-14866.409, Time=7.70 sec
 ARIMA(1,3,0)(0,0,0)[0] intercept   : AIC=-16157.403, Time=13.81 sec
 ARIMA(2,3,0)(0,0,0)[0] intercept   : AIC=-14855.623, Time=11.62 sec
 ARIMA(2,3,1)(0,0,0)[0] intercept   : AIC=-14720.644, Time=11.60 sec

Best model:  ARIMA(1,3,0)(0,0,0)[0] intercept
Total fit time: 124.355 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 0)   Log Likelihood                8103.701
Date:                Sun, 12 Dec 2021   AIC                         -16157.403
Time:                        18:04:04   BIC                         -16040.132
Sample:                             0   HQIC                        -16112.366
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
intercept  -2.802e-06   7.54e-07     -3.714      0.000   -4.28e-06   -1.32e-06
x1         -2.598e-05      0.001     -0.041      0.967      -0.001       0.001
x2         -2.599e-05      0.001     -0.047      0.963      -0.001       0.001
x3         -2.615e-05      0.001     -0.038      0.970      -0.001       0.001
x4             1.0000      0.001   1507.083      0.000       0.999       1.001
x5         -2.485e-05      0.001     -0.038      0.970      -0.001       0.001
x6         -2.807e-05   3.32e-05     -0.845      0.398   -9.32e-05    3.71e-05
x7         -2.593e-05   8.29e-05     -0.313      0.755      -0.000       0.000
x8             0.0019   7.15e-05     26.753      0.000       0.002       0.002
x9         -1.867e-06      0.001     -0.003      0.998      -0.001       0.001
x10            0.0003      0.000      0.644      0.520      -0.001       0.001
x11           -0.0025   8.93e-05    -28.145      0.000      -0.003      -0.002
x12            0.0015   8.06e-05     18.290      0.000       0.001       0.002
x13         -2.61e-05      0.000     -0.076      0.939      -0.001       0.001
x14        -7.719e-05      0.000     -0.374      0.708      -0.000       0.000
x15        -2.829e-05   8.57e-05     -0.330      0.741      -0.000       0.000
x16        -2.424e-05      0.000     -0.142      0.887      -0.000       0.000
x17        -2.292e-05   9.81e-05     -0.234      0.815      -0.000       0.000
x18         -4.39e-05      0.000     -0.429      0.668      -0.000       0.000
x19        -3.005e-05      0.000     -0.293      0.770      -0.000       0.000
x20         4.559e-05   9.36e-05      0.487      0.626      -0.000       0.000
x21        -7.981e-10      0.001  -9.88e-07      1.000      -0.002       0.002
x22        -1.557e-08      0.000     -0.000      1.000      -0.000       0.000
ar.L1         -0.6667   6.95e-05  -9587.073      0.000      -0.667      -0.667
sigma2      1.314e-10    7.8e-11      1.686      0.092   -2.14e-11    2.84e-10
===================================================================================
Ljung-Box (L1) (Q):                  90.59   Jarque-Bera (JB):           3138023.60
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.03   Skew:                             5.01
Prob(H) (two-sided):                  0.00   Kurtosis:                       308.71
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.36e+19. Standard errors may be unstable.
ARIMA order: (1, 3, 0) 


/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.01892, saving model to LSTM6.h5
48/48 - 7s - loss: 0.1326 - accuracy: 0.0000e+00 - val_loss: 0.0189 - val_accuracy: 0.0037 - lr: 0.0010 - 7s/epoch - 144ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.01892 to 0.00783, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0203 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 0.0010 - 235ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00783
48/48 - 0s - loss: 0.0349 - accuracy: 0.0000e+00 - val_loss: 0.0144 - val_accuracy: 0.0037 - lr: 0.0010 - 219ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00783
48/48 - 0s - loss: 0.0187 - accuracy: 0.0000e+00 - val_loss: 0.0234 - val_accuracy: 0.0037 - lr: 0.0010 - 216ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00783
48/48 - 0s - loss: 0.0109 - accuracy: 0.0000e+00 - val_loss: 0.1099 - val_accuracy: 0.0037 - lr: 0.0010 - 219ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00783
48/48 - 0s - loss: 0.0163 - accuracy: 0.0000e+00 - val_loss: 0.0212 - val_accuracy: 0.0037 - lr: 0.0010 - 217ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.00783
48/48 - 0s - loss: 0.0078 - accuracy: 0.0000e+00 - val_loss: 0.0930 - val_accuracy: 0.0037 - lr: 0.0010 - 217ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00783
48/48 - 0s - loss: 0.0162 - accuracy: 0.0000e+00 - val_loss: 0.0154 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 221ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00783
48/48 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0130 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 211ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00783
48/48 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 218ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.00783 to 0.00726, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 234ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.00726 to 0.00614, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 241ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.00614 to 0.00554, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 234ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.00554 to 0.00525, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 232ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.00525 to 0.00515, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 231ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00515
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 214ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00515
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 220ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00515
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 214ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00019: val_loss did not improve from 0.00515
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 225ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00515
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00515
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 211ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.9727e-04 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.9055e-04 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00024: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.8709e-04 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.8475e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.8283e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.8106e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.7934e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.7762e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.7588e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.7410e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.7230e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.7045e-04 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.6856e-04 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 212ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.6664e-04 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.6468e-04 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.6269e-04 - accuracy: 0.0000e+00 - val_loss: 0.0062 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.6065e-04 - accuracy: 0.0000e+00 - val_loss: 0.0062 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 211ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.5859e-04 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 212ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.5649e-04 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.5435e-04 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 212ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.5218e-04 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.4998e-04 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.4775e-04 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 210ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.4549e-04 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.4320e-04 - accuracy: 0.0000e+00 - val_loss: 0.0068 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.4088e-04 - accuracy: 0.0000e+00 - val_loss: 0.0069 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.3853e-04 - accuracy: 0.0000e+00 - val_loss: 0.0069 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.3616e-04 - accuracy: 0.0000e+00 - val_loss: 0.0070 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.3376e-04 - accuracy: 0.0000e+00 - val_loss: 0.0071 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 210ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.3134e-04 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.2890e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.2643e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.2394e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.2143e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.1891e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.1636e-04 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 216ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.1380e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.1123e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.0864e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.0604e-04 - accuracy: 0.0000e+00 - val_loss: 0.0082 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.0342e-04 - accuracy: 0.0000e+00 - val_loss: 0.0083 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00515
48/48 - 0s - loss: 9.0080e-04 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.00515
48/48 - 0s - loss: 8.9816e-04 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 210ms/epoch - 4ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00515
48/48 - 0s - loss: 8.9552e-04 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 00065: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 60.485697397526344 
RMSE:	 7.777255132598284 
MAPE:	 6.358945125308518
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.831, Time=2.77 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.20 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16288.946, Time=6.92 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=5.44 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16226.419, Time=9.82 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-13742.844, Time=8.63 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16101.256, Time=19.83 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17006.489, Time=2.65 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17002.686, Time=2.98 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17086.654, Time=7.24 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=-16097.512, Time=16.43 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17002.132, Time=3.36 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-17004.011, Time=4.11 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 94.420 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8570.327
Date:                Sun, 12 Dec 2021   AIC                         -17086.654
Time:                        18:06:47   BIC                         -16960.001
Sample:                             0   HQIC                        -17038.014
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -2.333e-10   9.31e-21  -2.51e+10      0.000   -2.33e-10   -2.33e-10
x2         -2.326e-10   9.29e-21   -2.5e+10      0.000   -2.33e-10   -2.33e-10
x3         -2.342e-10   9.32e-21  -2.51e+10      0.000   -2.34e-10   -2.34e-10
x4             1.0000   9.31e-21   1.07e+20      0.000       1.000       1.000
x5         -2.121e-10   8.87e-21  -2.39e+10      0.000   -2.12e-10   -2.12e-10
x6         -8.055e-10   1.64e-20   -4.9e+10      0.000   -8.05e-10   -8.05e-10
x7         -2.312e-10   9.27e-21  -2.49e+10      0.000   -2.31e-10   -2.31e-10
x8          -2.26e-10   9.17e-21  -2.47e+10      0.000   -2.26e-10   -2.26e-10
x9         -1.174e-11   1.86e-21   -6.3e+09      0.000   -1.17e-11   -1.17e-11
x10        -4.486e-11   3.98e-21  -1.13e+10      0.000   -4.49e-11   -4.49e-11
x11        -2.235e-10   9.11e-21  -2.45e+10      0.000   -2.23e-10   -2.23e-10
x12         -2.28e-10   9.21e-21  -2.48e+10      0.000   -2.28e-10   -2.28e-10
x13        -2.332e-10   9.31e-21  -2.51e+10      0.000   -2.33e-10   -2.33e-10
x14         -1.78e-09   2.57e-20  -6.92e+10      0.000   -1.78e-09   -1.78e-09
x15        -2.118e-10   8.84e-21   -2.4e+10      0.000   -2.12e-10   -2.12e-10
x16         -5.28e-10    1.4e-20  -3.76e+10      0.000   -5.28e-10   -5.28e-10
x17        -2.173e-10   8.94e-21  -2.43e+10      0.000   -2.17e-10   -2.17e-10
x18         -3.83e-11   3.74e-21  -1.02e+10      0.000   -3.83e-11   -3.83e-11
x19        -2.606e-10   9.86e-21  -2.64e+10      0.000   -2.61e-10   -2.61e-10
x20        -2.433e-10   9.48e-21  -2.57e+10      0.000   -2.43e-10   -2.43e-10
x21        -3.774e-13   1.42e-24  -2.65e+11      0.000   -3.77e-13   -3.77e-13
x22        -1.096e-11   1.35e-24  -8.11e+12      0.000    -1.1e-11    -1.1e-11
ar.L1         -0.4919    1.5e-22  -3.27e+21      0.000      -0.492      -0.492
ar.L2         -0.1922   8.41e-23  -2.28e+21      0.000      -0.192      -0.192
ar.L3         -0.0462   4.01e-23  -1.15e+21      0.000      -0.046      -0.046
ma.L1         -0.7070   3.34e-22  -2.12e+21      0.000      -0.707      -0.707
sigma2      8.977e-11   6.95e-11      1.291      0.197   -4.65e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  54.80   Jarque-Bera (JB):           4212163.49
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.43
Prob(H) (two-sided):                  0.00   Kurtosis:                       357.21
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 1.65e+43. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 


/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.13086, saving model to LSTM6.h5
16/16 - 4s - loss: 0.1233 - accuracy: 0.0000e+00 - val_loss: 0.1309 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 222ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.13086 to 0.06494, saving model to LSTM6.h5
16/16 - 0s - loss: 0.0611 - accuracy: 0.0000e+00 - val_loss: 0.0649 - val_accuracy: 0.0037 - lr: 0.0010 - 104ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.06494 to 0.00675, saving model to LSTM6.h5
16/16 - 0s - loss: 0.0231 - accuracy: 0.0000e+00 - val_loss: 0.0068 - val_accuracy: 0.0037 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.00675 to 0.00578, saving model to LSTM6.h5
16/16 - 0s - loss: 0.0055 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 0.0010 - 114ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00578
16/16 - 0s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0070 - val_accuracy: 0.0037 - lr: 0.0010 - 94ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.00578 to 0.00543, saving model to LSTM6.h5
16/16 - 0s - loss: 0.0035 - accuracy: 0.0000e+00 - val_loss: 0.0054 - val_accuracy: 0.0037 - lr: 0.0010 - 116ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00543
16/16 - 0s - loss: 0.0028 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 0.0010 - 94ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00543
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 0.0010 - 86ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00543
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0062 - val_accuracy: 0.0037 - lr: 0.0010 - 83ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00543
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 0.0010 - 88ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.00543
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 0.0010 - 84ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00543
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 91ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.1738e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 95ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.1280e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 92ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0773e-04 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 103ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0424e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 101ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0181e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0154e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0128e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0102e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0076e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0051e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00543
16/16 - 0s - loss: 9.0024e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9998e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9970e-04 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9942e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9914e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9884e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9855e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9824e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9794e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9762e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9730e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9698e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9665e-04 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9631e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9597e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9563e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9528e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9492e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9456e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9419e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9382e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9345e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9307e-04 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9269e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9230e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9190e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9150e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9110e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9070e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.9028e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.8987e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.8945e-04 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.8902e-04 - accuracy: 0.0000e+00 - val_loss: 0.0082 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00543
16/16 - 0s - loss: 8.8859e-04 - accuracy: 0.0000e+00 - val_loss: 0.0082 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 00056: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 60.485697397526344 
RMSE:	 7.777255132598284 
MAPE:	 6.358945125308518

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	43.66% Accuracy
MSE:	 58.20305175219876 
RMSE:	 7.629092459277103 
MAPE:	 6.21442849961768
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16080.357, Time=11.59 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14973.799, Time=6.15 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15549.629, Time=1.82 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15317.999, Time=8.46 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16061.924, Time=9.91 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15376.406, Time=14.46 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16186.215, Time=3.67 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-15308.706, Time=13.95 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-14920.393, Time=13.47 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-16184.203, Time=3.05 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 86.544 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8118.107
Date:                Sun, 12 Dec 2021   AIC                         -16186.215
Time:                        18:16:58   BIC                         -16068.944
Sample:                             0   HQIC                        -16141.178
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -9.919e-15      0.000   -8.4e-11      1.000      -0.000       0.000
x2          3.194e-15    6.3e-05   5.07e-11      1.000      -0.000       0.000
x3          3.066e-15   7.71e-05   3.98e-11      1.000      -0.000       0.000
x4             1.0000    4.4e-05   2.27e+04      0.000       1.000       1.000
x5         -3.977e-15   4.68e-05  -8.49e-11      1.000   -9.18e-05    9.18e-05
x6         -5.906e-17   8.34e-05  -7.08e-13      1.000      -0.000       0.000
x7         -8.726e-15   7.85e-05  -1.11e-10      1.000      -0.000       0.000
x8             0.0014   4.94e-05     27.704      0.000       0.001       0.001
x9         -3.542e-15      0.001  -2.63e-12      1.000      -0.003       0.003
x10           -0.0012      0.001     -1.566      0.117      -0.003       0.000
x11            0.0052   3.01e-05    172.396      0.000       0.005       0.005
x12           -0.0065      0.000    -49.747      0.000      -0.007      -0.006
x13         1.963e-14   7.85e-05    2.5e-10      1.000      -0.000       0.000
x14        -2.134e-14      0.000  -1.01e-10      1.000      -0.000       0.000
x15         3.464e-12      0.000   2.92e-08      1.000      -0.000       0.000
x16        -7.174e-13   6.45e-05  -1.11e-08      1.000      -0.000       0.000
x17         2.537e-13   7.42e-05   3.42e-09      1.000      -0.000       0.000
x18        -2.964e-15      0.000  -7.78e-12      1.000      -0.001       0.001
x19        -3.613e-12   8.67e-05  -4.17e-08      1.000      -0.000       0.000
x20         6.244e-14      0.000    2.1e-10      1.000      -0.001       0.001
x21        -4.242e-16      0.000  -1.47e-12      1.000      -0.001       0.001
x22        -2.128e-15      0.001  -1.74e-12      1.000      -0.002       0.002
ma.L1         -1.3894   4.16e-05  -3.34e+04      0.000      -1.389      -1.389
ma.L2          0.4036      0.000   3637.465      0.000       0.403       0.404
sigma2      1.287e-10   7.27e-11      1.770      0.077   -1.38e-11    2.71e-10
===================================================================================
Ljung-Box (L1) (Q):                  69.00   Jarque-Bera (JB):           6269147.49
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            12.07
Prob(H) (two-sided):                  0.00   Kurtosis:                       434.65
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 6.47e+20. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 


/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.00724, saving model to LSTM6.h5
17/17 - 4s - loss: 0.0847 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 0.0010 - 4s/epoch - 234ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.00724 to 0.00667, saving model to LSTM6.h5
17/17 - 0s - loss: 0.0178 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 0.0010 - 110ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.00667 to 0.00479, saving model to LSTM6.h5
17/17 - 0s - loss: 0.0044 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 0.0010 - 129ms/epoch - 8ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00479
17/17 - 0s - loss: 0.0071 - accuracy: 0.0000e+00 - val_loss: 0.0116 - val_accuracy: 0.0037 - lr: 0.0010 - 95ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.00479 to 0.00468, saving model to LSTM6.h5
17/17 - 0s - loss: 0.0029 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 0.0010 - 114ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0091 - accuracy: 0.0000e+00 - val_loss: 0.0309 - val_accuracy: 0.0037 - lr: 0.0010 - 99ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0137 - accuracy: 0.0000e+00 - val_loss: 0.0101 - val_accuracy: 0.0037 - lr: 0.0010 - 95ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0303 - accuracy: 0.0000e+00 - val_loss: 0.0959 - val_accuracy: 0.0037 - lr: 0.0010 - 91ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0281 - accuracy: 0.0000e+00 - val_loss: 0.0119 - val_accuracy: 0.0037 - lr: 0.0010 - 87ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00010: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0102 - accuracy: 0.0000e+00 - val_loss: 0.0545 - val_accuracy: 0.0037 - lr: 0.0010 - 94ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0064 - accuracy: 0.0000e+00 - val_loss: 0.0315 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 92ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0237 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 91ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0209 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 94ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 95ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00015: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0142 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 95ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0140 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0138 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0136 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0134 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00020: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0132 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0130 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0128 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0127 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0125 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0124 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0122 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0120 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0119 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0117 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0116 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0115 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0113 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0112 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0111 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0109 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0108 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0107 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00468
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0106 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.9588e-04 - accuracy: 0.0000e+00 - val_loss: 0.0105 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.9146e-04 - accuracy: 0.0000e+00 - val_loss: 0.0104 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.8725e-04 - accuracy: 0.0000e+00 - val_loss: 0.0103 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.8322e-04 - accuracy: 0.0000e+00 - val_loss: 0.0102 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.7939e-04 - accuracy: 0.0000e+00 - val_loss: 0.0101 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.7573e-04 - accuracy: 0.0000e+00 - val_loss: 0.0100 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.7224e-04 - accuracy: 0.0000e+00 - val_loss: 0.0099 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.6892e-04 - accuracy: 0.0000e+00 - val_loss: 0.0098 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.6575e-04 - accuracy: 0.0000e+00 - val_loss: 0.0097 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.6274e-04 - accuracy: 0.0000e+00 - val_loss: 0.0097 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.5986e-04 - accuracy: 0.0000e+00 - val_loss: 0.0096 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.5712e-04 - accuracy: 0.0000e+00 - val_loss: 0.0095 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.5451e-04 - accuracy: 0.0000e+00 - val_loss: 0.0095 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.5202e-04 - accuracy: 0.0000e+00 - val_loss: 0.0094 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.4965e-04 - accuracy: 0.0000e+00 - val_loss: 0.0094 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.4738e-04 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00468
17/17 - 0s - loss: 9.4522e-04 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 00055: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 60.485697397526344 
RMSE:	 7.777255132598284 
MAPE:	 6.358945125308518

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	43.66% Accuracy
MSE:	 58.20305175219876 
RMSE:	 7.629092459277103 
MAPE:	 6.21442849961768

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 70.88350276857014 
RMSE:	 8.419234096316014 
MAPE:	 6.6789569931753
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.780, Time=3.03 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.30 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15584.877, Time=8.29 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=6.19 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15271.475, Time=7.68 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15128.422, Time=9.76 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16352.675, Time=18.23 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17028.022, Time=4.55 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17002.621, Time=3.05 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17085.445, Time=6.59 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=15.40 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17001.997, Time=3.28 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16996.668, Time=4.00 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 94.368 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.723
Date:                Sun, 12 Dec 2021   AIC                         -17085.445
Time:                        18:22:36   BIC                         -16958.792
Sample:                             0   HQIC                        -17036.805
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1           -2.8e-10   1.36e-20  -2.05e+10      0.000    -2.8e-10    -2.8e-10
x2         -2.817e-10   1.37e-20  -2.06e+10      0.000   -2.82e-10   -2.82e-10
x3         -2.805e-10   1.36e-20  -2.06e+10      0.000    -2.8e-10    -2.8e-10
x4             1.0000   1.37e-20   7.33e+19      0.000       1.000       1.000
x5         -2.598e-10   1.31e-20  -1.98e+10      0.000    -2.6e-10    -2.6e-10
x6         -1.389e-09   2.98e-20  -4.66e+10      0.000   -1.39e-09   -1.39e-09
x7         -2.789e-10   1.36e-20  -2.05e+10      0.000   -2.79e-10   -2.79e-10
x8         -2.761e-10   1.35e-20  -2.04e+10      0.000   -2.76e-10   -2.76e-10
x9         -2.219e-12   3.36e-22   -6.6e+09      0.000   -2.22e-12   -2.22e-12
x10        -1.345e-10   9.37e-21  -1.43e+10      0.000   -1.34e-10   -1.34e-10
x11        -2.899e-10   1.39e-20  -2.09e+10      0.000    -2.9e-10    -2.9e-10
x12        -2.602e-10   1.32e-20  -1.98e+10      0.000    -2.6e-10    -2.6e-10
x13        -2.807e-10   1.36e-20  -2.06e+10      0.000   -2.81e-10   -2.81e-10
x14         -1.87e-09   3.52e-20  -5.31e+10      0.000   -1.87e-09   -1.87e-09
x15        -2.825e-10   1.37e-20  -2.07e+10      0.000   -2.82e-10   -2.82e-10
x16        -8.187e-11   7.33e-21  -1.12e+10      0.000   -8.19e-11   -8.19e-11
x17        -2.441e-10   1.27e-20  -1.92e+10      0.000   -2.44e-10   -2.44e-10
x18        -6.411e-10   2.06e-20  -3.11e+10      0.000   -6.41e-10   -6.41e-10
x19        -2.929e-10   1.39e-20  -2.11e+10      0.000   -2.93e-10   -2.93e-10
x20        -4.339e-10    1.7e-20  -2.56e+10      0.000   -4.34e-10   -4.34e-10
x21        -3.589e-13   2.52e-24  -1.42e+11      0.000   -3.59e-13   -3.59e-13
x22        -1.088e-11   2.36e-24   -4.6e+12      0.000   -1.09e-11   -1.09e-11
ar.L1         -0.4923   1.46e-22  -3.37e+21      0.000      -0.492      -0.492
ar.L2         -0.1923   8.47e-23  -2.27e+21      0.000      -0.192      -0.192
ar.L3         -0.0462   4.02e-23  -1.15e+21      0.000      -0.046      -0.046
ma.L1         -0.7077   3.31e-22  -2.14e+21      0.000      -0.708      -0.708
sigma2       8.99e-11   6.95e-11      1.293      0.196   -4.64e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  55.15   Jarque-Bera (JB):           4171184.78
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.27
Prob(H) (two-sided):                  0.00   Kurtosis:                       355.49
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.53e+42. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 


/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.21665, saving model to LSTM6.h5
10/10 - 4s - loss: 0.1989 - accuracy: 0.0000e+00 - val_loss: 0.2167 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 390ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.21665 to 0.00898, saving model to LSTM6.h5
10/10 - 0s - loss: 0.1270 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 0.0010 - 78ms/epoch - 8ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0819 - accuracy: 0.0000e+00 - val_loss: 0.1283 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 65ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0467 - accuracy: 0.0000e+00 - val_loss: 0.0334 - val_accuracy: 0.0037 - lr: 0.0010 - 66ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0154 - accuracy: 0.0000e+00 - val_loss: 0.0434 - val_accuracy: 0.0037 - lr: 0.0010 - 69ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0054 - accuracy: 0.0000e+00 - val_loss: 0.0271 - val_accuracy: 0.0037 - lr: 0.0010 - 68ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0274 - val_accuracy: 0.0037 - lr: 0.0010 - 69ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0284 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 69ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0293 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 70ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0300 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 60ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0304 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 58ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00012: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0308 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 65ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0308 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0308 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0309 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0309 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00017: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0309 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0310 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0310 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0310 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0311 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0311 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0311 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0312 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0312 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0312 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0313 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0313 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0314 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0314 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0314 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0315 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0315 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0315 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0316 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0316 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0317 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0317 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0317 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0318 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0318 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0318 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0319 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0319 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0319 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0320 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0320 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0320 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0321 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0321 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0321 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00898
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0322 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 00052: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 60.485697397526344 
RMSE:	 7.777255132598284 
MAPE:	 6.358945125308518

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	43.66% Accuracy
MSE:	 58.20305175219876 
RMSE:	 7.629092459277103 
MAPE:	 6.21442849961768

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 70.88350276857014 
RMSE:	 8.419234096316014 
MAPE:	 6.6789569931753

DEMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 119.53246002468391 
RMSE:	 10.933090140700566 
MAPE:	 9.747683697911842
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17059.325, Time=3.67 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.33 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16133.019, Time=6.02 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=5.66 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16091.980, Time=7.44 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16009.844, Time=12.43 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-15757.180, Time=8.86 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17029.439, Time=4.41 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17000.917, Time=3.48 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=45.027, Time=4.75 sec

Best model:  ARIMA(1,3,1)(0,0,0)[0]          
Total fit time: 61.075 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 1)   Log Likelihood                8554.662
Date:                Sun, 12 Dec 2021   AIC                         -17059.325
Time:                        18:32:29   BIC                         -16942.054
Sample:                             0   HQIC                        -17014.288
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -1.409e-10   5.52e-21  -2.55e+10      0.000   -1.41e-10   -1.41e-10
x2         -1.378e-10   5.47e-21  -2.52e+10      0.000   -1.38e-10   -1.38e-10
x3         -1.323e-10   5.35e-21  -2.47e+10      0.000   -1.32e-10   -1.32e-10
x4             1.0000   5.41e-21   1.85e+20      0.000       1.000       1.000
x5         -1.221e-10   5.15e-21  -2.37e+10      0.000   -1.22e-10   -1.22e-10
x6         -8.465e-10    1.3e-20  -6.53e+10      0.000   -8.47e-10   -8.47e-10
x7           -1.3e-10   5.32e-21  -2.44e+10      0.000    -1.3e-10    -1.3e-10
x8         -1.267e-10   5.27e-21  -2.41e+10      0.000   -1.27e-10   -1.27e-10
x9         -2.032e-11   6.67e-22  -3.05e+10      0.000   -2.03e-11   -2.03e-11
x10        -5.319e-11    2.3e-21  -2.31e+10      0.000   -5.32e-11   -5.32e-11
x11        -1.275e-10   5.28e-21  -2.42e+10      0.000   -1.28e-10   -1.28e-10
x12        -1.262e-10   5.23e-21  -2.41e+10      0.000   -1.26e-10   -1.26e-10
x13        -1.339e-10   5.39e-21  -2.49e+10      0.000   -1.34e-10   -1.34e-10
x14        -1.092e-09   1.55e-20  -7.06e+10      0.000   -1.09e-09   -1.09e-09
x15        -1.342e-10   5.42e-21  -2.48e+10      0.000   -1.34e-10   -1.34e-10
x16         -2.01e-10   6.63e-21  -3.03e+10      0.000   -2.01e-10   -2.01e-10
x17        -1.144e-10   5.01e-21  -2.29e+10      0.000   -1.14e-10   -1.14e-10
x18        -9.245e-11   4.49e-21  -2.06e+10      0.000   -9.24e-11   -9.24e-11
x19        -1.646e-10   6.01e-21  -2.74e+10      0.000   -1.65e-10   -1.65e-10
x20        -2.482e-10   7.35e-21  -3.37e+10      0.000   -2.48e-10   -2.48e-10
x21        -3.385e-12   3.14e-24  -1.08e+12      0.000   -3.39e-12   -3.39e-12
x22        -8.066e-11   2.47e-23  -3.26e+12      0.000   -8.07e-11   -8.07e-11
ar.L1         -0.2877   2.48e-22  -1.16e+21      0.000      -0.288      -0.288
ma.L1         -0.9134   1.05e-21   -8.7e+20      0.000      -0.913      -0.913
sigma2      9.332e-11   6.96e-11      1.340      0.180   -4.32e-11     2.3e-10
===================================================================================
Ljung-Box (L1) (Q):                  84.37   Jarque-Bera (JB):           4308764.36
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             5.22
Prob(H) (two-sided):                  0.00   Kurtosis:                       361.26
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.32e+42. Standard errors may be unstable.
ARIMA order: (1, 3, 1) 


/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.15069, saving model to LSTM6.h5
45/45 - 4s - loss: 0.1458 - accuracy: 0.0000e+00 - val_loss: 0.1507 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 82ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.15069 to 0.00809, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0958 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 0.0010 - 220ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00809
45/45 - 0s - loss: 0.0271 - accuracy: 0.0000e+00 - val_loss: 0.1124 - val_accuracy: 0.0037 - lr: 0.0010 - 208ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00809
45/45 - 0s - loss: 0.0220 - accuracy: 0.0000e+00 - val_loss: 0.0164 - val_accuracy: 0.0037 - lr: 0.0010 - 209ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00809
45/45 - 0s - loss: 0.0063 - accuracy: 0.0000e+00 - val_loss: 0.0540 - val_accuracy: 0.0037 - lr: 0.0010 - 212ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.00809 to 0.00341, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0078 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 0.0010 - 220ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0027 - accuracy: 0.0000e+00 - val_loss: 0.0291 - val_accuracy: 0.0037 - lr: 0.0010 - 205ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0041 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 0.0010 - 211ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0227 - val_accuracy: 0.0037 - lr: 0.0010 - 210ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0028 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 0.0010 - 206ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0197 - val_accuracy: 0.0037 - lr: 0.0010 - 206ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0054 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 206ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 208ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 206ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 206ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 211ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 199ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 207ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 208ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 209ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 207ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 202ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00341
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss improved from 0.00341 to 0.00341, saving model to LSTM6.h5
45/45 - 1s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 543ms/epoch - 12ms/step
Epoch 44/500

Epoch 00044: val_loss improved from 0.00341 to 0.00340, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss improved from 0.00340 to 0.00339, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss improved from 0.00339 to 0.00339, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss improved from 0.00339 to 0.00338, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 235ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss improved from 0.00338 to 0.00337, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss improved from 0.00337 to 0.00336, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss improved from 0.00336 to 0.00335, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 227ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss improved from 0.00335 to 0.00335, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss improved from 0.00335 to 0.00334, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss improved from 0.00334 to 0.00333, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss improved from 0.00333 to 0.00333, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss improved from 0.00333 to 0.00332, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss improved from 0.00332 to 0.00332, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss improved from 0.00332 to 0.00331, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 241ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss improved from 0.00331 to 0.00331, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss improved from 0.00331 to 0.00331, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss improved from 0.00331 to 0.00331, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss improved from 0.00331 to 0.00330, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss improved from 0.00330 to 0.00330, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss improved from 0.00330 to 0.00330, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss improved from 0.00330 to 0.00330, saving model to LSTM6.h5
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 208ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 5ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 201ms/epoch - 4ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 200ms/epoch - 4ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 208ms/epoch - 5ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 202ms/epoch - 4ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 209ms/epoch - 5ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.00330
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.9705e-04 - accuracy: 0.0000e+00 - val_loss: 0.0033 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.9169e-04 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 208ms/epoch - 5ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.8636e-04 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.8106e-04 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 209ms/epoch - 5ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.7579e-04 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.7056e-04 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 198ms/epoch - 4ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.6537e-04 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.6023e-04 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 201ms/epoch - 4ms/step
Epoch 84/500

Epoch 00084: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.5512e-04 - accuracy: 0.0000e+00 - val_loss: 0.0034 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 208ms/epoch - 5ms/step
Epoch 85/500

Epoch 00085: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.5006e-04 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 207ms/epoch - 5ms/step
Epoch 86/500

Epoch 00086: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.4505e-04 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 87/500

Epoch 00087: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.4009e-04 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 88/500

Epoch 00088: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.3518e-04 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 5ms/step
Epoch 89/500

Epoch 00089: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.3032e-04 - accuracy: 0.0000e+00 - val_loss: 0.0035 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 209ms/epoch - 5ms/step
Epoch 90/500

Epoch 00090: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.2551e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 91/500

Epoch 00091: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.2076e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 92/500

Epoch 00092: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.1606e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 93/500

Epoch 00093: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.1142e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 94/500

Epoch 00094: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.0684e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 95/500

Epoch 00095: val_loss did not improve from 0.00330
45/45 - 0s - loss: 9.0232e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 208ms/epoch - 5ms/step
Epoch 96/500

Epoch 00096: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.9786e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 97/500

Epoch 00097: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.9346e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 98/500

Epoch 00098: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.8912e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 99/500

Epoch 00099: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.8485e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 100/500

Epoch 00100: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.8064e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 101/500

Epoch 00101: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.7649e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 102/500

Epoch 00102: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.7241e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 103/500

Epoch 00103: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.6839e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 104/500

Epoch 00104: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.6444e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 105/500

Epoch 00105: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.6055e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 207ms/epoch - 5ms/step
Epoch 106/500

Epoch 00106: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.5673e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 216ms/epoch - 5ms/step
Epoch 107/500

Epoch 00107: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.5297e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 223ms/epoch - 5ms/step
Epoch 108/500

Epoch 00108: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.4928e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 109/500

Epoch 00109: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.4565e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 215ms/epoch - 5ms/step
Epoch 110/500

Epoch 00110: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.4208e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 111/500

Epoch 00111: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.3858e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 112/500

Epoch 00112: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.3515e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 202ms/epoch - 4ms/step
Epoch 113/500

Epoch 00113: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.3177e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 200ms/epoch - 4ms/step
Epoch 114/500

Epoch 00114: val_loss did not improve from 0.00330
45/45 - 0s - loss: 8.2846e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 00114: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 60.485697397526344 
RMSE:	 7.777255132598284 
MAPE:	 6.358945125308518

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	43.66% Accuracy
MSE:	 58.20305175219876 
RMSE:	 7.629092459277103 
MAPE:	 6.21442849961768

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 70.88350276857014 
RMSE:	 8.419234096316014 
MAPE:	 6.6789569931753

DEMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 119.53246002468391 
RMSE:	 10.933090140700566 
MAPE:	 9.747683697911842

KAMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 61.13308833987969 
RMSE:	 7.818765141624327 
MAPE:	 6.461585168646619
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.733, Time=2.82 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.592, Time=4.28 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15587.551, Time=7.81 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.592, Time=6.26 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16365.334, Time=10.33 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16163.760, Time=12.75 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16245.181, Time=15.13 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17028.017, Time=5.19 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17106.133, Time=6.00 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17085.425, Time=6.74 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=-17000.553, Time=3.99 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 81.307 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood                8579.066
Date:                Sun, 12 Dec 2021   AIC                         -17106.133
Time:                        18:37:13   BIC                         -16984.171
Sample:                             0   HQIC                        -17059.294
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -3.048e-10   1.69e-20   -1.8e+10      0.000   -3.05e-10   -3.05e-10
x2         -3.042e-10   1.75e-20  -1.74e+10      0.000   -3.04e-10   -3.04e-10
x3         -3.108e-10   1.62e-20  -1.92e+10      0.000   -3.11e-10   -3.11e-10
x4             1.0000   1.69e-20   5.91e+19      0.000       1.000       1.000
x5         -2.767e-10   1.61e-20  -1.72e+10      0.000   -2.77e-10   -2.77e-10
x6         -6.072e-09   1.38e-19  -4.42e+10      0.000   -6.07e-09   -6.07e-09
x7           -2.8e-10   1.62e-20  -1.73e+10      0.000    -2.8e-10    -2.8e-10
x8         -2.792e-10   1.65e-20  -1.69e+10      0.000   -2.79e-10   -2.79e-10
x9         -1.502e-10   1.02e-21  -1.48e+11      0.000    -1.5e-10    -1.5e-10
x10        -2.482e-10    4.3e-21  -5.77e+10      0.000   -2.48e-10   -2.48e-10
x11        -2.764e-10   1.64e-20  -1.69e+10      0.000   -2.76e-10   -2.76e-10
x12        -2.857e-10   1.64e-20  -1.74e+10      0.000   -2.86e-10   -2.86e-10
x13        -2.944e-10   1.66e-20  -1.77e+10      0.000   -2.94e-10   -2.94e-10
x14        -2.403e-09   4.86e-20  -4.95e+10      0.000    -2.4e-09    -2.4e-09
x15        -3.368e-10   1.81e-20  -1.86e+10      0.000   -3.37e-10   -3.37e-10
x16        -2.169e-10   1.45e-20  -1.49e+10      0.000   -2.17e-10   -2.17e-10
x17        -2.124e-10   1.44e-20  -1.47e+10      0.000   -2.12e-10   -2.12e-10
x18        -9.125e-10   2.98e-20  -3.06e+10      0.000   -9.13e-10   -9.13e-10
x19        -3.698e-10    1.9e-20  -1.95e+10      0.000    -3.7e-10    -3.7e-10
x20          -8.9e-10   2.94e-20  -3.03e+10      0.000    -8.9e-10    -8.9e-10
x21        -1.844e-11   1.86e-22   -9.9e+10      0.000   -1.84e-11   -1.84e-11
x22        -2.169e-10   5.04e-22   -4.3e+11      0.000   -2.17e-10   -2.17e-10
ar.L1         -1.2011    7.4e-23  -1.62e+22      0.000      -1.201      -1.201
ar.L2         -0.9017   1.51e-22  -5.98e+21      0.000      -0.902      -0.902
ar.L3         -0.4014   9.48e-23  -4.23e+21      0.000      -0.401      -0.401
sigma2      8.782e-11   6.95e-11      1.264      0.206   -4.84e-11    2.24e-10
===================================================================================
Ljung-Box (L1) (Q):                   3.61   Jarque-Bera (JB):             16191.93
Prob(Q):                              0.06   Prob(JB):                         0.00
Heteroskedasticity (H):               0.35   Skew:                             0.59
Prob(H) (two-sided):                  0.00   Kurtosis:                        24.94
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 3.23e+40. Standard errors may be unstable.
ARIMA order: (3, 3, 0) 


/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.12328, saving model to LSTM6.h5
58/58 - 4s - loss: 0.1831 - accuracy: 0.0000e+00 - val_loss: 0.1233 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 65ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.12328 to 0.00640, saving model to LSTM6.h5
58/58 - 0s - loss: 0.0502 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 0.0010 - 284ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00640
58/58 - 0s - loss: 0.0100 - accuracy: 0.0000e+00 - val_loss: 0.0400 - val_accuracy: 0.0037 - lr: 0.0010 - 255ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00640
58/58 - 0s - loss: 0.0156 - accuracy: 0.0000e+00 - val_loss: 0.0123 - val_accuracy: 0.0037 - lr: 0.0010 - 270ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00640
58/58 - 0s - loss: 0.0069 - accuracy: 0.0000e+00 - val_loss: 0.0534 - val_accuracy: 0.0037 - lr: 0.0010 - 279ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00640
58/58 - 0s - loss: 0.0139 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 0.0010 - 266ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.00640
58/58 - 0s - loss: 0.0069 - accuracy: 0.0000e+00 - val_loss: 0.0328 - val_accuracy: 0.0037 - lr: 0.0010 - 259ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.00640 to 0.00547, saving model to LSTM6.h5
58/58 - 0s - loss: 0.0213 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 298ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.00547 to 0.00539, saving model to LSTM6.h5
58/58 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0054 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 299ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.00539 to 0.00500, saving model to LSTM6.h5
58/58 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 278ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.00500 to 0.00486, saving model to LSTM6.h5
58/58 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 296ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.00486 to 0.00482, saving model to LSTM6.h5
58/58 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 293ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00482
58/58 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 261ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00482
58/58 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 261ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00482
58/58 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0051 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 277ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.00482
58/58 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 278ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00482
58/58 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.7738e-04 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.6520e-04 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.6009e-04 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 272ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.5750e-04 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 264ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.5583e-04 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 272ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.5451e-04 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 277ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.5333e-04 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 264ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.5220e-04 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 261ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.5107e-04 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 283ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.4994e-04 - accuracy: 0.0000e+00 - val_loss: 0.0054 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 279ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.4879e-04 - accuracy: 0.0000e+00 - val_loss: 0.0054 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 255ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.4761e-04 - accuracy: 0.0000e+00 - val_loss: 0.0054 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.4640e-04 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 285ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.4517e-04 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.4390e-04 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 253ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.4261e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 273ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.4128e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 276ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.3993e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 268ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.3854e-04 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 287ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.3711e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 281ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.3566e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 251ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.3417e-04 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 263ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.3265e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.3110e-04 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 272ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.2951e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.2789e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.2623e-04 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 263ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.2454e-04 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.2282e-04 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 261ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.2106e-04 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 253ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.1927e-04 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.1744e-04 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 255ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.1558e-04 - accuracy: 0.0000e+00 - val_loss: 0.0062 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.1369e-04 - accuracy: 0.0000e+00 - val_loss: 0.0062 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.1177e-04 - accuracy: 0.0000e+00 - val_loss: 0.0062 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.0981e-04 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 258ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.0783e-04 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 263ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.0581e-04 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.0376e-04 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 261ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00482
58/58 - 0s - loss: 9.0169e-04 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00482
58/58 - 0s - loss: 8.9959e-04 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 278ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00482
58/58 - 0s - loss: 8.9745e-04 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00482
58/58 - 0s - loss: 8.9530e-04 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 261ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00482
58/58 - 0s - loss: 8.9312e-04 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 253ms/epoch - 4ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00482
58/58 - 0s - loss: 8.9091e-04 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 260ms/epoch - 4ms/step
Epoch 00062: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 60.485697397526344 
RMSE:	 7.777255132598284 
MAPE:	 6.358945125308518

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	43.66% Accuracy
MSE:	 58.20305175219876 
RMSE:	 7.629092459277103 
MAPE:	 6.21442849961768

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 70.88350276857014 
RMSE:	 8.419234096316014 
MAPE:	 6.6789569931753

DEMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 119.53246002468391 
RMSE:	 10.933090140700566 
MAPE:	 9.747683697911842

KAMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 61.13308833987969 
RMSE:	 7.818765141624327 
MAPE:	 6.461585168646619

MIDPOINT
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 61.5384692642518 
RMSE:	 7.8446458979517875 
MAPE:	 6.407298993379305
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16954.347, Time=2.33 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14725.736, Time=2.40 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16732.390, Time=7.97 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15913.358, Time=6.88 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16550.077, Time=10.20 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15004.835, Time=9.37 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16027.273, Time=9.76 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-16934.995, Time=2.32 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16924.758, Time=3.64 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=-16952.347, Time=2.30 sec

Best model:  ARIMA(1,3,1)(0,0,0)[0]          
Total fit time: 57.183 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 1)   Log Likelihood                8502.173
Date:                Sun, 12 Dec 2021   AIC                         -16954.347
Time:                        18:40:27   BIC                         -16837.076
Sample:                             0   HQIC                        -16909.310
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1          3.409e-14   2.62e-06    1.3e-08      1.000   -5.13e-06    5.13e-06
x2          1.816e-14   2.62e-06   6.93e-09      1.000   -5.13e-06    5.13e-06
x3         -2.039e-15   2.47e-06  -8.26e-10      1.000   -4.84e-06    4.84e-06
x4             1.0000    2.5e-06      4e+05      0.000       1.000       1.000
x5          2.488e-12   2.48e-06      1e-06      1.000   -4.86e-06    4.86e-06
x6           2.84e-15   6.48e-06   4.38e-10      1.000   -1.27e-05    1.27e-05
x7          3.618e-13   3.24e-06   1.12e-07      1.000   -6.36e-06    6.36e-06
x8            -0.0002   4.44e-06    -43.079      0.000      -0.000      -0.000
x9           2.93e-14    6.3e-08   4.65e-07      1.000   -1.23e-07    1.23e-07
x10        -2.843e-05   9.63e-06     -2.951      0.003   -4.73e-05   -9.55e-06
x11            0.0002   3.28e-06     53.981      0.000       0.000       0.000
x12            0.0001   5.63e-06     23.078      0.000       0.000       0.000
x13        -2.595e-14   2.63e-06  -9.88e-09      1.000   -5.15e-06    5.15e-06
x14        -6.497e-14   5.76e-06  -1.13e-08      1.000   -1.13e-05    1.13e-05
x15         1.699e-12   3.08e-06   5.51e-07      1.000   -6.04e-06    6.04e-06
x16        -3.969e-12   4.77e-06  -8.33e-07      1.000   -9.34e-06    9.34e-06
x17         5.452e-12   8.58e-07   6.35e-06      1.000   -1.68e-06    1.68e-06
x18         -3.68e-13   1.33e-05  -2.76e-08      1.000   -2.61e-05    2.61e-05
x19        -5.643e-13   4.61e-06  -1.22e-07      1.000   -9.03e-06    9.03e-06
x20         6.651e-14    4.9e-05   1.36e-09      1.000   -9.61e-05    9.61e-05
x21         -1.76e-16   8.47e-11  -2.08e-06      1.000   -1.66e-10    1.66e-10
x22         -7.82e-16   1.75e-10  -4.47e-06      1.000   -3.43e-10    3.43e-10
ar.L1         -0.2858   5.46e-08  -5.24e+06      0.000      -0.286      -0.286
ma.L1         -0.9143   5.59e-08  -1.63e+07      0.000      -0.914      -0.914
sigma2          1e-10   6.99e-11      1.430      0.153   -3.71e-11    2.37e-10
===================================================================================
Ljung-Box (L1) (Q):                  84.00   Jarque-Bera (JB):           4822228.07
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            -6.05
Prob(H) (two-sided):                  0.00   Kurtosis:                       381.97
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 3.54e+27. Standard errors may be unstable.
ARIMA order: (1, 3, 1) 


/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.09054, saving model to LSTM6.h5
43/43 - 4s - loss: 0.1402 - accuracy: 0.0000e+00 - val_loss: 0.0905 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 86ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.09054 to 0.00550, saving model to LSTM6.h5
43/43 - 0s - loss: 0.0382 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 0.0010 - 232ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00550
43/43 - 0s - loss: 0.0291 - accuracy: 0.0000e+00 - val_loss: 0.1315 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 206ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00550
43/43 - 0s - loss: 0.0341 - accuracy: 0.0000e+00 - val_loss: 0.0183 - val_accuracy: 0.0037 - lr: 0.0010 - 212ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00550
43/43 - 0s - loss: 0.0166 - accuracy: 0.0000e+00 - val_loss: 0.1407 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 219ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.00550 to 0.00397, saving model to LSTM6.h5
43/43 - 0s - loss: 0.0172 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 0.0010 - 231ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0062 - accuracy: 0.0000e+00 - val_loss: 0.0553 - val_accuracy: 0.0037 - lr: 0.0010 - 203ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0073 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 0.0010 - 198ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0028 - accuracy: 0.0000e+00 - val_loss: 0.0323 - val_accuracy: 0.0037 - lr: 0.0010 - 196ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0036 - accuracy: 0.0000e+00 - val_loss: 0.0129 - val_accuracy: 0.0037 - lr: 0.0010 - 211ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0272 - val_accuracy: 0.0037 - lr: 0.0010 - 221ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0070 - accuracy: 0.0000e+00 - val_loss: 0.0107 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 194ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 198ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 196ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 220ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 216ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 200ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 197ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0051 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 192ms/epoch - 4ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 196ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 215ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 238ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 199ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 201ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 195ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 227ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 216ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 193ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 196ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 197ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 198ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 197ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 199ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 201ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 200ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 194ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 213ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 194ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00397
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 198ms/epoch - 5ms/step
Epoch 00056: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 60.485697397526344 
RMSE:	 7.777255132598284 
MAPE:	 6.358945125308518

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	43.66% Accuracy
MSE:	 58.20305175219876 
RMSE:	 7.629092459277103 
MAPE:	 6.21442849961768

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 70.88350276857014 
RMSE:	 8.419234096316014 
MAPE:	 6.6789569931753

DEMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 119.53246002468391 
RMSE:	 10.933090140700566 
MAPE:	 9.747683697911842

KAMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 61.13308833987969 
RMSE:	 7.818765141624327 
MAPE:	 6.461585168646619

MIDPOINT
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 61.5384692642518 
RMSE:	 7.8446458979517875 
MAPE:	 6.407298993379305

T3
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 163.02597008234568 
RMSE:	 12.768162361214932 
MAPE:	 10.498544939048504
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16412.930, Time=10.23 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14867.265, Time=6.41 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15902.803, Time=5.45 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15117.003, Time=6.98 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15669.652, Time=7.65 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-12676.374, Time=8.53 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16418.724, Time=9.53 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-15107.772, Time=12.50 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15708.742, Time=15.20 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-13418.641, Time=23.25 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 105.756 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8234.362
Date:                Sun, 12 Dec 2021   AIC                         -16418.724
Time:                        18:45:30   BIC                         -16301.453
Sample:                             0   HQIC                        -16373.687
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -1.784e-07      0.001     -0.000      1.000      -0.002       0.002
x2         -1.784e-07      0.001     -0.000      1.000      -0.003       0.003
x3         -1.794e-07      0.001     -0.000      1.000      -0.002       0.002
x4             1.0000      0.000   2616.546      0.000       0.999       1.001
x5         -1.704e-07      0.000     -0.000      1.000      -0.001       0.001
x6         -2.858e-07   3.31e-05     -0.009      0.993   -6.52e-05    6.46e-05
x7         -1.754e-07      0.001     -0.000      1.000      -0.002       0.002
x8             0.0007      0.000      3.091      0.002       0.000       0.001
x9          3.313e-08      0.000   9.39e-05      1.000      -0.001       0.001
x10         3.499e-06      0.000      0.022      0.983      -0.000       0.000
x11           -0.0003      0.000     -1.284      0.199      -0.001       0.000
x12        -6.362e-05      0.000     -0.260      0.795      -0.001       0.000
x13        -1.783e-07      0.000     -0.001      0.999      -0.000       0.000
x14        -5.244e-07      0.001     -0.001      0.999      -0.001       0.001
x15        -1.737e-07      0.000     -0.001      0.999      -0.000       0.000
x16        -2.583e-07      0.000     -0.001      0.999      -0.000       0.000
x17         -1.74e-07      0.000     -0.001      0.999      -0.000       0.000
x18        -5.776e-08      0.000     -0.000      1.000      -0.000       0.000
x19         -1.95e-07      0.000     -0.002      0.999      -0.000       0.000
x20          1.72e-07      0.000      0.001      0.999      -0.000       0.000
x21        -7.548e-10      0.001  -9.93e-07      1.000      -0.001       0.001
x22        -1.194e-08      0.000  -8.47e-05      1.000      -0.000       0.000
ma.L1         -1.3862   1.58e-05  -8.78e+04      0.000      -1.386      -1.386
ma.L2          0.4019   4.28e-05   9396.834      0.000       0.402       0.402
sigma2      1.265e-10   7.58e-11      1.669      0.095    -2.2e-11    2.75e-10
===================================================================================
Ljung-Box (L1) (Q):                  66.79   Jarque-Bera (JB):           5900482.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                           -11.32
Prob(H) (two-sided):                  0.00   Kurtosis:                       421.81
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.07e+19. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 


/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.10823, saving model to LSTM6.h5
90/90 - 4s - loss: 0.1248 - accuracy: 0.0000e+00 - val_loss: 0.1082 - val_accuracy: 0.0037 - lr: 0.0010 - 4s/epoch - 46ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.10823 to 0.01063, saving model to LSTM6.h5
90/90 - 0s - loss: 0.0325 - accuracy: 0.0000e+00 - val_loss: 0.0106 - val_accuracy: 0.0037 - lr: 0.0010 - 409ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01063
90/90 - 0s - loss: 0.0327 - accuracy: 0.0000e+00 - val_loss: 0.0371 - val_accuracy: 0.0037 - lr: 0.0010 - 397ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.01063 to 0.00919, saving model to LSTM6.h5
90/90 - 0s - loss: 0.0261 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 0.0010 - 413ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00919
90/90 - 0s - loss: 0.0209 - accuracy: 0.0000e+00 - val_loss: 0.0125 - val_accuracy: 0.0037 - lr: 0.0010 - 390ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.00919 to 0.00721, saving model to LSTM6.h5
90/90 - 0s - loss: 0.0180 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 0.0010 - 423ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00721
90/90 - 0s - loss: 0.0141 - accuracy: 0.0000e+00 - val_loss: 0.0101 - val_accuracy: 0.0037 - lr: 0.0010 - 406ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00721
90/90 - 0s - loss: 0.0121 - accuracy: 0.0000e+00 - val_loss: 0.0096 - val_accuracy: 0.0037 - lr: 0.0010 - 390ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00721
90/90 - 0s - loss: 0.0108 - accuracy: 0.0000e+00 - val_loss: 0.0138 - val_accuracy: 0.0037 - lr: 0.0010 - 398ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00721
90/90 - 0s - loss: 0.0104 - accuracy: 0.0000e+00 - val_loss: 0.0150 - val_accuracy: 0.0037 - lr: 0.0010 - 392ms/epoch - 4ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.00721
90/90 - 0s - loss: 0.0103 - accuracy: 0.0000e+00 - val_loss: 0.0197 - val_accuracy: 0.0037 - lr: 0.0010 - 400ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.00721 to 0.00668, saving model to LSTM6.h5
90/90 - 0s - loss: 0.0150 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 398ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0037 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 394ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0027 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 381ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0107 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 388ms/epoch - 4ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0122 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 390ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00017: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0137 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 394ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0138 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 389ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0139 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0140 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 4ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0141 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 389ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00022: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0142 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 385ms/epoch - 4ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0144 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 389ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0145 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 383ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0147 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 388ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0148 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0150 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0152 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 390ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0154 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 390ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0156 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 383ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0158 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 386ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0161 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0163 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 398ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0171 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 396ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00668
90/90 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0174 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 385ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.9880e-04 - accuracy: 0.0000e+00 - val_loss: 0.0176 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.9158e-04 - accuracy: 0.0000e+00 - val_loss: 0.0179 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 389ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.8459e-04 - accuracy: 0.0000e+00 - val_loss: 0.0182 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.7781e-04 - accuracy: 0.0000e+00 - val_loss: 0.0185 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.7124e-04 - accuracy: 0.0000e+00 - val_loss: 0.0188 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.6490e-04 - accuracy: 0.0000e+00 - val_loss: 0.0192 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.5877e-04 - accuracy: 0.0000e+00 - val_loss: 0.0195 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 389ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.5285e-04 - accuracy: 0.0000e+00 - val_loss: 0.0198 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 385ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.4714e-04 - accuracy: 0.0000e+00 - val_loss: 0.0201 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 397ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.4163e-04 - accuracy: 0.0000e+00 - val_loss: 0.0205 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.3632e-04 - accuracy: 0.0000e+00 - val_loss: 0.0208 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 388ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.3120e-04 - accuracy: 0.0000e+00 - val_loss: 0.0211 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.2627e-04 - accuracy: 0.0000e+00 - val_loss: 0.0215 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 385ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.2152e-04 - accuracy: 0.0000e+00 - val_loss: 0.0218 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.1695e-04 - accuracy: 0.0000e+00 - val_loss: 0.0222 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 388ms/epoch - 4ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.1254e-04 - accuracy: 0.0000e+00 - val_loss: 0.0225 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 388ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.0830e-04 - accuracy: 0.0000e+00 - val_loss: 0.0228 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.0420e-04 - accuracy: 0.0000e+00 - val_loss: 0.0232 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 386ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00668
90/90 - 0s - loss: 9.0026e-04 - accuracy: 0.0000e+00 - val_loss: 0.0235 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 388ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00668
90/90 - 0s - loss: 8.9645e-04 - accuracy: 0.0000e+00 - val_loss: 0.0239 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00668
90/90 - 0s - loss: 8.9277e-04 - accuracy: 0.0000e+00 - val_loss: 0.0242 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 399ms/epoch - 4ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00668
90/90 - 0s - loss: 8.8922e-04 - accuracy: 0.0000e+00 - val_loss: 0.0245 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00668
90/90 - 0s - loss: 8.8578e-04 - accuracy: 0.0000e+00 - val_loss: 0.0248 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 383ms/epoch - 4ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00668
90/90 - 0s - loss: 8.8246e-04 - accuracy: 0.0000e+00 - val_loss: 0.0252 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 396ms/epoch - 4ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00668
90/90 - 0s - loss: 8.7923e-04 - accuracy: 0.0000e+00 - val_loss: 0.0255 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 391ms/epoch - 4ms/step
Epoch 00062: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 60.485697397526344 
RMSE:	 7.777255132598284 
MAPE:	 6.358945125308518

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	43.66% Accuracy
MSE:	 58.20305175219876 
RMSE:	 7.629092459277103 
MAPE:	 6.21442849961768

WMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 70.88350276857014 
RMSE:	 8.419234096316014 
MAPE:	 6.6789569931753

DEMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 119.53246002468391 
RMSE:	 10.933090140700566 
MAPE:	 9.747683697911842

KAMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 61.13308833987969 
RMSE:	 7.818765141624327 
MAPE:	 6.461585168646619

MIDPOINT
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 61.5384692642518 
RMSE:	 7.8446458979517875 
MAPE:	 6.407298993379305

T3
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 163.02597008234568 
RMSE:	 12.768162361214932 
MAPE:	 10.498544939048504

TEMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 66.14227466119469 
RMSE:	 8.132790090811067 
MAPE:	 7.1170786919128775
Runtime: mins: 47.84116581131666

Architecture Used

In [ ]:
from google.colab import files
import cv2
uploaded = files.upload()
Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to enable. 
Saving Experiment6.png to Experiment6 (2).png
In [ ]:
img = cv2.imread('Experiment6.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)
Out[ ]:
<matplotlib.image.AxesImage at 0x7fcec1090550>

Model Plots

In [109]:
with open('simulation6_data.json') as json_file:
    simulation6 = json.load(json_file)
fileimg = 'Experiment6'
In [110]:
for i in range(len(list(simulation6.keys()))):
  SIM = list(simulation6.keys())[i]
  plot_train(simulation6,SIM)
  plot_test(simulation6,SIM)

----- Train RMSE for SMA ----- 8.82965892571068
----- Train_MSE_LSTM for SMA ----- 77.96287674438227
----- Train MAE LSTM for SMA ----- 7.7139597657818975

----- Test RMSE for SMA----- 7.777255132598284
----- Test_MSE_LSTM for SMA----- 60.485697397526344
----- Test_MAE_LSTM for SMA----- 6.358945125308518

----- Train RMSE for EMA ----- 10.171315551915972
----- Train_MSE_LSTM for EMA ----- 103.45566005664772
----- Train MAE LSTM for EMA ----- 8.993942033814147

----- Test RMSE for EMA----- 7.629092459277103
----- Test_MSE_LSTM for EMA----- 58.20305175219876
----- Test_MAE_LSTM for EMA----- 6.21442849961768

----- Train RMSE for WMA ----- 10.41897039644979
----- Train_MSE_LSTM for WMA ----- 108.5549441220971
----- Train MAE LSTM for WMA ----- 9.308931496257705

----- Test RMSE for WMA----- 8.419234096316014
----- Test_MSE_LSTM for WMA----- 70.88350276857014
----- Test_MAE_LSTM for WMA----- 6.6789569931753

----- Train RMSE for DEMA ----- 12.03541858653864
----- Train_MSE_LSTM for DEMA ----- 144.85130055319976
----- Train MAE LSTM for DEMA ----- 10.796683445353278

----- Test RMSE for DEMA----- 10.933090140700566
----- Test_MSE_LSTM for DEMA----- 119.53246002468391
----- Test_MAE_LSTM for DEMA----- 9.747683697911842

----- Train RMSE for KAMA ----- 10.508593318849396
----- Train_MSE_LSTM for KAMA ----- 110.43053354096617
----- Train MAE LSTM for KAMA ----- 9.452300205135183

----- Test RMSE for KAMA----- 7.818765141624327
----- Test_MSE_LSTM for KAMA----- 61.13308833987969
----- Test_MAE_LSTM for KAMA----- 6.461585168646619

----- Train RMSE for MIDPOINT ----- 9.440601010764405
----- Train_MSE_LSTM for MIDPOINT ----- 89.12494744444592
----- Train MAE LSTM for MIDPOINT ----- 8.391389348327055

----- Test RMSE for MIDPOINT----- 7.8446458979517875
----- Test_MSE_LSTM for MIDPOINT----- 61.5384692642518
----- Test_MAE_LSTM for MIDPOINT----- 6.407298993379305

----- Train RMSE for T3 ----- 11.992355702371695
----- Train_MSE_LSTM for T3 ----- 143.81659529220693
----- Train MAE LSTM for T3 ----- 10.767362229981385

----- Test RMSE for T3----- 12.768162361214932
----- Test_MSE_LSTM for T3----- 163.02597008234568
----- Test_MAE_LSTM for T3----- 10.498544939048504

----- Train RMSE for TEMA ----- 7.421204593553642
----- Train_MSE_LSTM for TEMA ----- 55.07427761938168
----- Train MAE LSTM for TEMA ----- 5.137645379344801

----- Test RMSE for TEMA----- 8.132790090811067
----- Test_MSE_LSTM for TEMA----- 66.14227466119469
----- Test_MAE_LSTM for TEMA----- 7.1170786919128775

Arima w Exogenous Variable Multistep MutiVariate LSTM Hybrid Model Experiment 7

In [ ]:
def get_arima_exog(dataframe,original_data, train_len, test_len):    
    

    # prepare train and test data for exogenous vr
    X_value = pd.DataFrame(low_vol.iloc[:, :])
    y_value = pd.DataFrame(low_vol.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    X_scale_dataset = X_scaler.fit_transform(X_value)
    y_scale_dataset = y_scaler.fit_transform(y_value)
    # Get data and check shape
    # X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X_scale_dataset)
    y_train, y_test, = split_train_test(y_scale_dataset)
    yc_train,yc_test = split_train_test(low_vol_data)
    yc = yc_test.values.tolist()
    y_train_list = y_train.flatten().tolist()
    y_test_list = y_test.flatten().tolist()
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

    # Initialize model
    model = auto_arima(y_train_list,exogenous  = X_train,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
            suppress_warnings=True,stepwise=True,seasonal=True)

      # Determine model parameters
    print(model.summary())
    model.fit(y_train_list,maxiter=200)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

      # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
        model = pmdarima.ARIMA(order=order)
        model.fit(y_train_list)
        # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')

        prediction.append(model.predict()[0])
        y_train_list.append(y_test_list[i])

    predictionte = y_scaler.inverse_transform(np.array(prediction).reshape(-1,1))
    y_test_ = y_scaler.inverse_transform(np.array(y_test_list).reshape(-1,1))

    # Generate error data
    mse = mean_squared_error(yc_test, predictionte)
    rmse = mse ** 0.5
    mae = mean_absolute_error(y_test_ , predictionte )
    return yc,predictionte.flatten().tolist(), mse, rmse, mae
In [ ]:
def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det =20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM7.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma+' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 3
    # define custom activation
    # 
    class Double_Tanh(Activation):
        def __init__(self, activation, **kwargs):
            super(Double_Tanh, self).__init__(activation, **kwargs)
            self.__name__ = 'double_tanh'

    def double_tanh(x):
        return (K.tanh(x) * 2)

    get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
        # Model Generation
    model = Sequential()
    #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    model.add(Dense(1))
    model.add(Activation(double_tanh))
    model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM7.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te
In [ ]:
if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation7 = {}
    imgfile = 'Experiment7'
    for ma in optimized_period:
                print(ma)
                print(functions[ma])
                print ( int( optimized_period[ma]))
              # if ma == 'SMA':
                low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
                low_vol = low_vol.fillna(0)
                low_vol_data = df['close']
                high_vol = pd.DataFrame()
                df2 = df.copy()
                for i in df2.columns:
                  if i in low_vol.columns:
                    high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
                high_vol_data = df['close']
                ## *****************************************************
                # Generate ARIMA and LSTM predictions
                print('\nWorking on ' + ma + ' predictions')
                try:
                  print('parameters used : ', train_len, test_len)
                  low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima_exog(low_vol,low_vol_data, train_len, test_len)
                except:
                    print('ARIMA error, skipping to next MA type')
                    continue
                Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
                final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
                mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
                rmse_ftr = mse_ftr ** 0.5
                mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
                mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

                final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
                mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
                rmse = mse ** 0.5
                mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                # Generate prediction accuracy
                actual = df['close'].tail(test_len).values
                result_1 = []
                result_2 = []
                for i in range(1, len(final_prediction)):
                    # Compare prediction to previous close price
                    if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                        result_1.append(1)
                    elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                        result_1.append(1)
                    else:
                        result_1.append(0)

                    # Compare prediction to previous prediction
                    if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                        result_2.append(1)
                    elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                        result_2.append(1)
                    else:
                        result_2.append(0)

                accuracy_1 = np.mean(result_1)
                accuracy_2 = np.mean(result_2)

                simulation7[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                              'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                  'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                              'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                  'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                              'rmse': rmse_ftr, 'mae' : mae_ftr},
                                  'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                            'rmse': rmse, 'mae': mae },
                                  'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

                # save simulation data here as checkpoint
                with open('simulation7_data.json', 'w') as fp:
                    json.dump(simulation7, fp)

                for ma in simulation7.keys():
                    print('\n' + ma)
                    print('Prediction vs Close:\t\t' + str(round(100*simulation7[ma]['accuracy']['prediction vs close'], 2))
                          + '% Accuracy')
                    print('Prediction vs Prediction:\t' + str(round(100*simulation7[ma]['accuracy']['prediction vs prediction'], 2))
                          + '% Accuracy')
                    print('MSE:\t', simulation7[ma]['final']['mse'],
                          '\nRMSE:\t', simulation7[ma]['final']['rmse'],
                          '\nMAPE:\t', simulation7[ma]['final']['mae'])#,
                          # '\nMAPE:\t', simulation[ma]['final']['mape'])
              # else:
              #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-14771.778, Time=12.60 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14135.387, Time=6.27 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15280.870, Time=10.58 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15393.475, Time=8.23 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-14981.217, Time=5.02 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14516.868, Time=13.87 sec
 ARIMA(0,3,1)(0,0,0)[0] intercept   : AIC=-15663.967, Time=10.19 sec
 ARIMA(0,3,0)(0,0,0)[0] intercept   : AIC=-13838.679, Time=5.27 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=-14734.479, Time=6.54 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-14866.409, Time=7.59 sec
 ARIMA(1,3,0)(0,0,0)[0] intercept   : AIC=-16157.403, Time=13.73 sec
 ARIMA(2,3,0)(0,0,0)[0] intercept   : AIC=-14855.623, Time=10.93 sec
 ARIMA(2,3,1)(0,0,0)[0] intercept   : AIC=-14720.644, Time=11.37 sec

Best model:  ARIMA(1,3,0)(0,0,0)[0] intercept
Total fit time: 122.215 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 0)   Log Likelihood                8103.701
Date:                Sun, 12 Dec 2021   AIC                         -16157.403
Time:                        18:54:25   BIC                         -16040.132
Sample:                             0   HQIC                        -16112.366
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
intercept  -2.802e-06   7.54e-07     -3.714      0.000   -4.28e-06   -1.32e-06
x1         -2.598e-05      0.001     -0.041      0.967      -0.001       0.001
x2         -2.599e-05      0.001     -0.047      0.963      -0.001       0.001
x3         -2.615e-05      0.001     -0.038      0.970      -0.001       0.001
x4             1.0000      0.001   1507.083      0.000       0.999       1.001
x5         -2.485e-05      0.001     -0.038      0.970      -0.001       0.001
x6         -2.807e-05   3.32e-05     -0.845      0.398   -9.32e-05    3.71e-05
x7         -2.593e-05   8.29e-05     -0.313      0.755      -0.000       0.000
x8             0.0019   7.15e-05     26.753      0.000       0.002       0.002
x9         -1.867e-06      0.001     -0.003      0.998      -0.001       0.001
x10            0.0003      0.000      0.644      0.520      -0.001       0.001
x11           -0.0025   8.93e-05    -28.145      0.000      -0.003      -0.002
x12            0.0015   8.06e-05     18.290      0.000       0.001       0.002
x13         -2.61e-05      0.000     -0.076      0.939      -0.001       0.001
x14        -7.719e-05      0.000     -0.374      0.708      -0.000       0.000
x15        -2.829e-05   8.57e-05     -0.330      0.741      -0.000       0.000
x16        -2.424e-05      0.000     -0.142      0.887      -0.000       0.000
x17        -2.292e-05   9.81e-05     -0.234      0.815      -0.000       0.000
x18         -4.39e-05      0.000     -0.429      0.668      -0.000       0.000
x19        -3.005e-05      0.000     -0.293      0.770      -0.000       0.000
x20         4.559e-05   9.36e-05      0.487      0.626      -0.000       0.000
x21        -7.981e-10      0.001  -9.88e-07      1.000      -0.002       0.002
x22        -1.557e-08      0.000     -0.000      1.000      -0.000       0.000
ar.L1         -0.6667   6.95e-05  -9587.073      0.000      -0.667      -0.667
sigma2      1.314e-10    7.8e-11      1.686      0.092   -2.14e-11    2.84e-10
===================================================================================
Ljung-Box (L1) (Q):                  90.59   Jarque-Bera (JB):           3138023.60
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.03   Skew:                             5.01
Prob(H) (two-sided):                  0.00   Kurtosis:                       308.71
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.36e+19. Standard errors may be unstable.
ARIMA order: (1, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.51163, saving model to LSTM7.h5
48/48 - 3s - loss: 0.0787 - mse: 0.0787 - mae: 0.2232 - val_loss: 0.5116 - val_mse: 0.5116 - val_mae: 0.6749 - lr: 0.0010 - 3s/epoch - 54ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.51163 to 0.10215, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0240 - mse: 0.0240 - mae: 0.1254 - val_loss: 0.1022 - val_mse: 0.1022 - val_mae: 0.2690 - lr: 0.0010 - 187ms/epoch - 4ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.10215 to 0.08625, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0239 - mse: 0.0239 - mae: 0.1220 - val_loss: 0.0862 - val_mse: 0.0862 - val_mae: 0.2475 - lr: 0.0010 - 183ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.08625 to 0.08622, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0209 - mse: 0.0209 - mae: 0.1105 - val_loss: 0.0862 - val_mse: 0.0862 - val_mae: 0.2503 - lr: 0.0010 - 184ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.08622 to 0.05556, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0170 - mse: 0.0170 - mae: 0.1013 - val_loss: 0.0556 - val_mse: 0.0556 - val_mae: 0.1965 - lr: 0.0010 - 183ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.05556
48/48 - 0s - loss: 0.0150 - mse: 0.0150 - mae: 0.0951 - val_loss: 0.0736 - val_mse: 0.0736 - val_mae: 0.2312 - lr: 0.0010 - 174ms/epoch - 4ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.05556 to 0.05386, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0176 - mse: 0.0176 - mae: 0.0998 - val_loss: 0.0539 - val_mse: 0.0539 - val_mae: 0.1947 - lr: 0.0010 - 204ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05386
48/48 - 0s - loss: 0.0178 - mse: 0.0178 - mae: 0.0999 - val_loss: 0.0788 - val_mse: 0.0788 - val_mae: 0.2416 - lr: 0.0010 - 171ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.05386 to 0.03839, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0188 - mse: 0.0188 - mae: 0.1056 - val_loss: 0.0384 - val_mse: 0.0384 - val_mae: 0.1620 - lr: 0.0010 - 189ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.03839
48/48 - 0s - loss: 0.0161 - mse: 0.0161 - mae: 0.0995 - val_loss: 0.0913 - val_mse: 0.0913 - val_mae: 0.2627 - lr: 0.0010 - 172ms/epoch - 4ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.03839 to 0.02747, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0226 - mse: 0.0226 - mae: 0.1166 - val_loss: 0.0275 - val_mse: 0.0275 - val_mae: 0.1359 - lr: 0.0010 - 185ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.02747
48/48 - 0s - loss: 0.0181 - mse: 0.0181 - mae: 0.1066 - val_loss: 0.0737 - val_mse: 0.0737 - val_mae: 0.2324 - lr: 0.0010 - 182ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.02747 to 0.02661, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0239 - mse: 0.0239 - mae: 0.1240 - val_loss: 0.0266 - val_mse: 0.0266 - val_mae: 0.1316 - lr: 0.0010 - 186ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.02661
48/48 - 0s - loss: 0.0213 - mse: 0.0213 - mae: 0.1188 - val_loss: 0.0989 - val_mse: 0.0989 - val_mae: 0.2754 - lr: 0.0010 - 179ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.02661 to 0.01829, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0232 - mse: 0.0232 - mae: 0.1254 - val_loss: 0.0183 - val_mse: 0.0183 - val_mae: 0.1067 - lr: 0.0010 - 203ms/epoch - 4ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.01829
48/48 - 0s - loss: 0.0196 - mse: 0.0196 - mae: 0.1180 - val_loss: 0.1224 - val_mse: 0.1224 - val_mae: 0.3113 - lr: 0.0010 - 173ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01829
48/48 - 0s - loss: 0.0210 - mse: 0.0210 - mae: 0.1213 - val_loss: 0.0197 - val_mse: 0.0197 - val_mae: 0.1084 - lr: 0.0010 - 174ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01829
48/48 - 0s - loss: 0.0156 - mse: 0.0156 - mae: 0.1043 - val_loss: 0.1529 - val_mse: 0.1529 - val_mae: 0.3513 - lr: 0.0010 - 174ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.01829 to 0.01744, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0173 - mse: 0.0173 - mae: 0.1106 - val_loss: 0.0174 - val_mse: 0.0174 - val_mae: 0.1021 - lr: 0.0010 - 180ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0125 - mse: 0.0125 - mae: 0.0923 - val_loss: 0.1679 - val_mse: 0.1679 - val_mae: 0.3697 - lr: 0.0010 - 174ms/epoch - 4ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0146 - mse: 0.0146 - mae: 0.1007 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1205 - lr: 0.0010 - 172ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0840 - val_loss: 0.1515 - val_mse: 0.1515 - val_mae: 0.3473 - lr: 0.0010 - 174ms/epoch - 4ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0849 - val_loss: 0.0436 - val_mse: 0.0436 - val_mae: 0.1599 - lr: 0.0010 - 175ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00024: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0752 - val_loss: 0.1504 - val_mse: 0.1504 - val_mae: 0.3461 - lr: 0.0010 - 175ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0128 - mse: 0.0128 - mae: 0.0910 - val_loss: 0.1090 - val_mse: 0.1090 - val_mae: 0.2871 - lr: 1.0000e-04 - 172ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0608 - val_loss: 0.0960 - val_mse: 0.0960 - val_mae: 0.2657 - lr: 1.0000e-04 - 175ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.0889 - val_mse: 0.0889 - val_mae: 0.2534 - lr: 1.0000e-04 - 173ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0534 - val_loss: 0.0851 - val_mse: 0.0851 - val_mae: 0.2463 - lr: 1.0000e-04 - 177ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00029: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0563 - val_loss: 0.0812 - val_mse: 0.0812 - val_mae: 0.2388 - lr: 1.0000e-04 - 175ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0525 - val_loss: 0.0809 - val_mse: 0.0809 - val_mae: 0.2383 - lr: 1.0000e-05 - 174ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0535 - val_loss: 0.0805 - val_mse: 0.0805 - val_mae: 0.2376 - lr: 1.0000e-05 - 174ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0538 - val_loss: 0.0802 - val_mse: 0.0802 - val_mae: 0.2369 - lr: 1.0000e-05 - 174ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0535 - val_loss: 0.0800 - val_mse: 0.0800 - val_mae: 0.2366 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00034: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0529 - val_loss: 0.0799 - val_mse: 0.0799 - val_mae: 0.2364 - lr: 1.0000e-05 - 177ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0532 - val_loss: 0.0798 - val_mse: 0.0798 - val_mae: 0.2361 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0522 - val_loss: 0.0794 - val_mse: 0.0794 - val_mae: 0.2355 - lr: 1.0000e-05 - 175ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0533 - val_loss: 0.0795 - val_mse: 0.0795 - val_mae: 0.2355 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0555 - val_loss: 0.0794 - val_mse: 0.0794 - val_mae: 0.2353 - lr: 1.0000e-05 - 172ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0502 - val_loss: 0.0793 - val_mse: 0.0793 - val_mae: 0.2351 - lr: 1.0000e-05 - 176ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0518 - val_loss: 0.0790 - val_mse: 0.0790 - val_mae: 0.2346 - lr: 1.0000e-05 - 174ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0517 - val_loss: 0.0788 - val_mse: 0.0788 - val_mae: 0.2342 - lr: 1.0000e-05 - 175ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.0789 - val_mse: 0.0789 - val_mae: 0.2344 - lr: 1.0000e-05 - 171ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0542 - val_loss: 0.0787 - val_mse: 0.0787 - val_mae: 0.2339 - lr: 1.0000e-05 - 172ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0521 - val_loss: 0.0786 - val_mse: 0.0786 - val_mae: 0.2337 - lr: 1.0000e-05 - 176ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.0784 - val_mse: 0.0784 - val_mae: 0.2332 - lr: 1.0000e-05 - 175ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0528 - val_loss: 0.0783 - val_mse: 0.0783 - val_mae: 0.2330 - lr: 1.0000e-05 - 176ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0522 - val_loss: 0.0784 - val_mse: 0.0784 - val_mae: 0.2332 - lr: 1.0000e-05 - 172ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0512 - val_loss: 0.0785 - val_mse: 0.0785 - val_mae: 0.2333 - lr: 1.0000e-05 - 169ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0543 - val_loss: 0.0785 - val_mse: 0.0785 - val_mae: 0.2334 - lr: 1.0000e-05 - 172ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0513 - val_loss: 0.0788 - val_mse: 0.0788 - val_mae: 0.2338 - lr: 1.0000e-05 - 178ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0533 - val_loss: 0.0784 - val_mse: 0.0784 - val_mae: 0.2330 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0531 - val_loss: 0.0787 - val_mse: 0.0787 - val_mae: 0.2337 - lr: 1.0000e-05 - 185ms/epoch - 4ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0514 - val_loss: 0.0786 - val_mse: 0.0786 - val_mae: 0.2335 - lr: 1.0000e-05 - 190ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0530 - val_loss: 0.0786 - val_mse: 0.0786 - val_mae: 0.2334 - lr: 1.0000e-05 - 179ms/epoch - 4ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0541 - val_loss: 0.0787 - val_mse: 0.0787 - val_mae: 0.2336 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0540 - val_loss: 0.0787 - val_mse: 0.0787 - val_mae: 0.2335 - lr: 1.0000e-05 - 179ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0555 - val_loss: 0.0786 - val_mse: 0.0786 - val_mae: 0.2334 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0518 - val_loss: 0.0787 - val_mse: 0.0787 - val_mae: 0.2336 - lr: 1.0000e-05 - 174ms/epoch - 4ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0502 - val_loss: 0.0785 - val_mse: 0.0785 - val_mae: 0.2332 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0534 - val_loss: 0.0778 - val_mse: 0.0778 - val_mae: 0.2319 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0522 - val_loss: 0.0780 - val_mse: 0.0780 - val_mae: 0.2321 - lr: 1.0000e-05 - 171ms/epoch - 4ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0536 - val_loss: 0.0778 - val_mse: 0.0778 - val_mae: 0.2318 - lr: 1.0000e-05 - 179ms/epoch - 4ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0543 - val_loss: 0.0776 - val_mse: 0.0776 - val_mae: 0.2314 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0522 - val_loss: 0.0774 - val_mse: 0.0774 - val_mae: 0.2309 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0527 - val_loss: 0.0772 - val_mse: 0.0772 - val_mae: 0.2305 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0553 - val_loss: 0.0770 - val_mse: 0.0770 - val_mae: 0.2300 - lr: 1.0000e-05 - 177ms/epoch - 4ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0531 - val_loss: 0.0773 - val_mse: 0.0773 - val_mae: 0.2306 - lr: 1.0000e-05 - 182ms/epoch - 4ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0513 - val_loss: 0.0779 - val_mse: 0.0779 - val_mae: 0.2317 - lr: 1.0000e-05 - 174ms/epoch - 4ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.01744
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0521 - val_loss: 0.0783 - val_mse: 0.0783 - val_mae: 0.2325 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 00069: early stopping

SMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 23.38002191723926 
RMSE:	 4.835289227878645 
MAPE:	 3.8675720673818827
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.831, Time=2.51 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.39 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16288.946, Time=7.13 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=5.85 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16226.419, Time=11.51 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-13742.844, Time=8.75 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16101.256, Time=19.30 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17006.489, Time=2.83 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17002.686, Time=3.23 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17086.654, Time=6.68 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=-16097.512, Time=16.53 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17002.132, Time=3.74 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-17004.011, Time=4.35 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 96.817 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8570.327
Date:                Sun, 12 Dec 2021   AIC                         -17086.654
Time:                        18:57:07   BIC                         -16960.001
Sample:                             0   HQIC                        -17038.014
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -2.333e-10   9.31e-21  -2.51e+10      0.000   -2.33e-10   -2.33e-10
x2         -2.326e-10   9.29e-21   -2.5e+10      0.000   -2.33e-10   -2.33e-10
x3         -2.342e-10   9.32e-21  -2.51e+10      0.000   -2.34e-10   -2.34e-10
x4             1.0000   9.31e-21   1.07e+20      0.000       1.000       1.000
x5         -2.121e-10   8.87e-21  -2.39e+10      0.000   -2.12e-10   -2.12e-10
x6         -8.055e-10   1.64e-20   -4.9e+10      0.000   -8.05e-10   -8.05e-10
x7         -2.312e-10   9.27e-21  -2.49e+10      0.000   -2.31e-10   -2.31e-10
x8          -2.26e-10   9.17e-21  -2.47e+10      0.000   -2.26e-10   -2.26e-10
x9         -1.174e-11   1.86e-21   -6.3e+09      0.000   -1.17e-11   -1.17e-11
x10        -4.486e-11   3.98e-21  -1.13e+10      0.000   -4.49e-11   -4.49e-11
x11        -2.235e-10   9.11e-21  -2.45e+10      0.000   -2.23e-10   -2.23e-10
x12         -2.28e-10   9.21e-21  -2.48e+10      0.000   -2.28e-10   -2.28e-10
x13        -2.332e-10   9.31e-21  -2.51e+10      0.000   -2.33e-10   -2.33e-10
x14         -1.78e-09   2.57e-20  -6.92e+10      0.000   -1.78e-09   -1.78e-09
x15        -2.118e-10   8.84e-21   -2.4e+10      0.000   -2.12e-10   -2.12e-10
x16         -5.28e-10    1.4e-20  -3.76e+10      0.000   -5.28e-10   -5.28e-10
x17        -2.173e-10   8.94e-21  -2.43e+10      0.000   -2.17e-10   -2.17e-10
x18         -3.83e-11   3.74e-21  -1.02e+10      0.000   -3.83e-11   -3.83e-11
x19        -2.606e-10   9.86e-21  -2.64e+10      0.000   -2.61e-10   -2.61e-10
x20        -2.433e-10   9.48e-21  -2.57e+10      0.000   -2.43e-10   -2.43e-10
x21        -3.774e-13   1.42e-24  -2.65e+11      0.000   -3.77e-13   -3.77e-13
x22        -1.096e-11   1.35e-24  -8.11e+12      0.000    -1.1e-11    -1.1e-11
ar.L1         -0.4919    1.5e-22  -3.27e+21      0.000      -0.492      -0.492
ar.L2         -0.1922   8.41e-23  -2.28e+21      0.000      -0.192      -0.192
ar.L3         -0.0462   4.01e-23  -1.15e+21      0.000      -0.046      -0.046
ma.L1         -0.7070   3.34e-22  -2.12e+21      0.000      -0.707      -0.707
sigma2      8.977e-11   6.95e-11      1.291      0.197   -4.65e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  54.80   Jarque-Bera (JB):           4212163.49
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.43
Prob(H) (two-sided):                  0.00   Kurtosis:                       357.21
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 1.65e+43. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.31018, saving model to LSTM7.h5
16/16 - 2s - loss: 0.0462 - mse: 0.0462 - mae: 0.1644 - val_loss: 0.3102 - val_mse: 0.3102 - val_mae: 0.5170 - lr: 0.0010 - 2s/epoch - 137ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.31018 to 0.08240, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0570 - mse: 0.0570 - mae: 0.1988 - val_loss: 0.0824 - val_mse: 0.0824 - val_mae: 0.2560 - lr: 0.0010 - 84ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.08240 to 0.05511, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0147 - mse: 0.0147 - mae: 0.0971 - val_loss: 0.0551 - val_mse: 0.0551 - val_mae: 0.2073 - lr: 0.0010 - 86ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.05511 to 0.02778, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0170 - mse: 0.0170 - mae: 0.1049 - val_loss: 0.0278 - val_mse: 0.0278 - val_mae: 0.1439 - lr: 0.0010 - 87ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.02778 to 0.02773, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0112 - mse: 0.0112 - mae: 0.0858 - val_loss: 0.0277 - val_mse: 0.0277 - val_mae: 0.1434 - lr: 0.0010 - 83ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.02773 to 0.02567, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0104 - mse: 0.0104 - mae: 0.0793 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1374 - lr: 0.0010 - 116ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0095 - mse: 0.0095 - mae: 0.0771 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1380 - lr: 0.0010 - 83ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0087 - mse: 0.0087 - mae: 0.0746 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1437 - lr: 0.0010 - 80ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0092 - mse: 0.0092 - mae: 0.0763 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1454 - lr: 0.0010 - 78ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0708 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1508 - lr: 0.0010 - 83ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0089 - mse: 0.0089 - mae: 0.0762 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1528 - lr: 0.0010 - 79ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0701 - val_loss: 0.0306 - val_mse: 0.0306 - val_mae: 0.1499 - lr: 1.0000e-04 - 71ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0673 - val_loss: 0.0299 - val_mse: 0.0299 - val_mae: 0.1480 - lr: 1.0000e-04 - 74ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0671 - val_loss: 0.0297 - val_mse: 0.0297 - val_mae: 0.1475 - lr: 1.0000e-04 - 69ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0623 - val_loss: 0.0304 - val_mse: 0.0304 - val_mae: 0.1492 - lr: 1.0000e-04 - 73ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0634 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1505 - lr: 1.0000e-04 - 73ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0602 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1506 - lr: 1.0000e-05 - 71ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0642 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1506 - lr: 1.0000e-05 - 74ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0635 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1506 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0632 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1506 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0623 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1508 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0636 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1509 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0636 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1509 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0667 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1510 - lr: 1.0000e-05 - 74ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0620 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1511 - lr: 1.0000e-05 - 72ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0626 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1511 - lr: 1.0000e-05 - 71ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0619 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1512 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0644 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1514 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0637 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1514 - lr: 1.0000e-05 - 72ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0616 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1514 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0657 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1512 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0632 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1510 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0646 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1511 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0606 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1512 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0639 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1510 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0662 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1511 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0619 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1512 - lr: 1.0000e-05 - 72ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0618 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1511 - lr: 1.0000e-05 - 71ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0627 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1512 - lr: 1.0000e-05 - 71ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0626 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1512 - lr: 1.0000e-05 - 71ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0625 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1513 - lr: 1.0000e-05 - 72ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0618 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1514 - lr: 1.0000e-05 - 70ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0635 - val_loss: 0.0313 - val_mse: 0.0313 - val_mae: 0.1515 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0623 - val_loss: 0.0313 - val_mse: 0.0313 - val_mae: 0.1515 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0614 - val_loss: 0.0313 - val_mse: 0.0313 - val_mae: 0.1515 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0616 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1518 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0629 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1521 - lr: 1.0000e-05 - 73ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0645 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1524 - lr: 1.0000e-05 - 69ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0632 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1523 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0637 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1525 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0650 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1526 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0641 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1526 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0638 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1525 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0640 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1524 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0615 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1527 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.02567
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0633 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1529 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 00056: early stopping

SMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 23.38002191723926 
RMSE:	 4.835289227878645 
MAPE:	 3.8675720673818827

EMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 35.056668726825066 
RMSE:	 5.920867227596399 
MAPE:	 4.704877912816018
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16080.357, Time=11.01 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14973.799, Time=5.84 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15549.629, Time=1.74 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15317.999, Time=8.07 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16061.924, Time=9.28 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15376.406, Time=14.58 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16186.215, Time=3.34 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-15308.706, Time=13.75 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-14920.393, Time=13.37 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-16184.203, Time=2.99 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 83.993 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8118.107
Date:                Sun, 12 Dec 2021   AIC                         -16186.215
Time:                        19:06:46   BIC                         -16068.944
Sample:                             0   HQIC                        -16141.178
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -9.919e-15      0.000   -8.4e-11      1.000      -0.000       0.000
x2          3.194e-15    6.3e-05   5.07e-11      1.000      -0.000       0.000
x3          3.066e-15   7.71e-05   3.98e-11      1.000      -0.000       0.000
x4             1.0000    4.4e-05   2.27e+04      0.000       1.000       1.000
x5         -3.977e-15   4.68e-05  -8.49e-11      1.000   -9.18e-05    9.18e-05
x6         -5.906e-17   8.34e-05  -7.08e-13      1.000      -0.000       0.000
x7         -8.726e-15   7.85e-05  -1.11e-10      1.000      -0.000       0.000
x8             0.0014   4.94e-05     27.704      0.000       0.001       0.001
x9         -3.542e-15      0.001  -2.63e-12      1.000      -0.003       0.003
x10           -0.0012      0.001     -1.566      0.117      -0.003       0.000
x11            0.0052   3.01e-05    172.396      0.000       0.005       0.005
x12           -0.0065      0.000    -49.747      0.000      -0.007      -0.006
x13         1.963e-14   7.85e-05    2.5e-10      1.000      -0.000       0.000
x14        -2.134e-14      0.000  -1.01e-10      1.000      -0.000       0.000
x15         3.464e-12      0.000   2.92e-08      1.000      -0.000       0.000
x16        -7.174e-13   6.45e-05  -1.11e-08      1.000      -0.000       0.000
x17         2.537e-13   7.42e-05   3.42e-09      1.000      -0.000       0.000
x18        -2.964e-15      0.000  -7.78e-12      1.000      -0.001       0.001
x19        -3.613e-12   8.67e-05  -4.17e-08      1.000      -0.000       0.000
x20         6.244e-14      0.000    2.1e-10      1.000      -0.001       0.001
x21        -4.242e-16      0.000  -1.47e-12      1.000      -0.001       0.001
x22        -2.128e-15      0.001  -1.74e-12      1.000      -0.002       0.002
ma.L1         -1.3894   4.16e-05  -3.34e+04      0.000      -1.389      -1.389
ma.L2          0.4036      0.000   3637.465      0.000       0.403       0.404
sigma2      1.287e-10   7.27e-11      1.770      0.077   -1.38e-11    2.71e-10
===================================================================================
Ljung-Box (L1) (Q):                  69.00   Jarque-Bera (JB):           6269147.49
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            12.07
Prob(H) (two-sided):                  0.00   Kurtosis:                       434.65
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 6.47e+20. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.16222, saving model to LSTM7.h5
17/17 - 3s - loss: 0.2269 - mse: 0.2269 - mae: 0.3844 - val_loss: 0.1622 - val_mse: 0.1622 - val_mae: 0.3887 - lr: 0.0010 - 3s/epoch - 151ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.16222 to 0.14651, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0613 - mse: 0.0613 - mae: 0.2144 - val_loss: 0.1465 - val_mse: 0.1465 - val_mae: 0.3680 - lr: 0.0010 - 86ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.14651 to 0.11348, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0237 - mse: 0.0237 - mae: 0.1218 - val_loss: 0.1135 - val_mse: 0.1135 - val_mae: 0.3203 - lr: 0.0010 - 91ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.11348 to 0.07060, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0231 - mse: 0.0231 - mae: 0.1214 - val_loss: 0.0706 - val_mse: 0.0706 - val_mae: 0.2457 - lr: 0.0010 - 95ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.07060 to 0.06062, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0175 - mse: 0.0175 - mae: 0.1070 - val_loss: 0.0606 - val_mse: 0.0606 - val_mae: 0.2244 - lr: 0.0010 - 88ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.06062 to 0.04813, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0165 - mse: 0.0165 - mae: 0.1023 - val_loss: 0.0481 - val_mse: 0.0481 - val_mae: 0.1959 - lr: 0.0010 - 90ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04813
17/17 - 0s - loss: 0.0149 - mse: 0.0149 - mae: 0.0990 - val_loss: 0.0483 - val_mse: 0.0483 - val_mae: 0.1965 - lr: 0.0010 - 77ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.04813 to 0.04461, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0151 - mse: 0.0151 - mae: 0.0979 - val_loss: 0.0446 - val_mse: 0.0446 - val_mae: 0.1874 - lr: 0.0010 - 87ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04461
17/17 - 0s - loss: 0.0117 - mse: 0.0117 - mae: 0.0869 - val_loss: 0.0475 - val_mse: 0.0475 - val_mae: 0.1943 - lr: 0.0010 - 72ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.04461 to 0.04192, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0129 - mse: 0.0129 - mae: 0.0900 - val_loss: 0.0419 - val_mse: 0.0419 - val_mae: 0.1804 - lr: 0.0010 - 89ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0115 - mse: 0.0115 - mae: 0.0854 - val_loss: 0.0447 - val_mse: 0.0447 - val_mae: 0.1875 - lr: 0.0010 - 75ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0109 - mse: 0.0109 - mae: 0.0841 - val_loss: 0.0463 - val_mse: 0.0463 - val_mae: 0.1918 - lr: 0.0010 - 72ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0101 - mse: 0.0101 - mae: 0.0805 - val_loss: 0.0501 - val_mse: 0.0501 - val_mae: 0.2007 - lr: 0.0010 - 74ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0101 - mse: 0.0101 - mae: 0.0802 - val_loss: 0.0472 - val_mse: 0.0472 - val_mae: 0.1935 - lr: 0.0010 - 79ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00015: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0092 - mse: 0.0092 - mae: 0.0771 - val_loss: 0.0539 - val_mse: 0.0539 - val_mae: 0.2088 - lr: 0.0010 - 77ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0096 - mse: 0.0096 - mae: 0.0766 - val_loss: 0.0531 - val_mse: 0.0531 - val_mae: 0.2070 - lr: 1.0000e-04 - 82ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0086 - mse: 0.0086 - mae: 0.0732 - val_loss: 0.0516 - val_mse: 0.0516 - val_mae: 0.2038 - lr: 1.0000e-04 - 79ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0742 - val_loss: 0.0511 - val_mse: 0.0511 - val_mae: 0.2026 - lr: 1.0000e-04 - 81ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0086 - mse: 0.0086 - mae: 0.0725 - val_loss: 0.0510 - val_mse: 0.0510 - val_mae: 0.2024 - lr: 1.0000e-04 - 80ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00020: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0716 - val_loss: 0.0513 - val_mse: 0.0513 - val_mae: 0.2032 - lr: 1.0000e-04 - 75ms/epoch - 4ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0756 - val_loss: 0.0514 - val_mse: 0.0514 - val_mae: 0.2033 - lr: 1.0000e-05 - 74ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0087 - mse: 0.0087 - mae: 0.0747 - val_loss: 0.0513 - val_mse: 0.0513 - val_mae: 0.2033 - lr: 1.0000e-05 - 73ms/epoch - 4ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0085 - mse: 0.0085 - mae: 0.0725 - val_loss: 0.0513 - val_mse: 0.0513 - val_mae: 0.2032 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0708 - val_loss: 0.0514 - val_mse: 0.0514 - val_mae: 0.2033 - lr: 1.0000e-05 - 75ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00025: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0713 - val_loss: 0.0514 - val_mse: 0.0514 - val_mae: 0.2034 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0084 - mse: 0.0084 - mae: 0.0716 - val_loss: 0.0514 - val_mse: 0.0514 - val_mae: 0.2035 - lr: 1.0000e-05 - 76ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0713 - val_loss: 0.0515 - val_mse: 0.0515 - val_mae: 0.2036 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0089 - mse: 0.0089 - mae: 0.0743 - val_loss: 0.0515 - val_mse: 0.0515 - val_mae: 0.2036 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0706 - val_loss: 0.0515 - val_mse: 0.0515 - val_mae: 0.2036 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0710 - val_loss: 0.0516 - val_mse: 0.0516 - val_mae: 0.2038 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0715 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2041 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0084 - mse: 0.0084 - mae: 0.0736 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2040 - lr: 1.0000e-05 - 76ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0721 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2040 - lr: 1.0000e-05 - 73ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0723 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2040 - lr: 1.0000e-05 - 76ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0722 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2041 - lr: 1.0000e-05 - 76ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0710 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2041 - lr: 1.0000e-05 - 71ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0706 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2042 - lr: 1.0000e-05 - 72ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0720 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2041 - lr: 1.0000e-05 - 75ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0732 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2042 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0698 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2041 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0705 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2042 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0706 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2042 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0714 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2041 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0711 - val_loss: 0.0516 - val_mse: 0.0516 - val_mae: 0.2040 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0725 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2040 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0766 - val_loss: 0.0516 - val_mse: 0.0516 - val_mae: 0.2040 - lr: 1.0000e-05 - 74ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0722 - val_loss: 0.0516 - val_mse: 0.0516 - val_mae: 0.2040 - lr: 1.0000e-05 - 75ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0691 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2041 - lr: 1.0000e-05 - 74ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0712 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2040 - lr: 1.0000e-05 - 75ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0684 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2042 - lr: 1.0000e-05 - 75ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0703 - val_loss: 0.0519 - val_mse: 0.0519 - val_mae: 0.2045 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0700 - val_loss: 0.0519 - val_mse: 0.0519 - val_mae: 0.2047 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0687 - val_loss: 0.0520 - val_mse: 0.0520 - val_mae: 0.2048 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0711 - val_loss: 0.0520 - val_mse: 0.0520 - val_mae: 0.2049 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0693 - val_loss: 0.0521 - val_mse: 0.0521 - val_mae: 0.2050 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0696 - val_loss: 0.0521 - val_mse: 0.0521 - val_mae: 0.2051 - lr: 1.0000e-05 - 76ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0704 - val_loss: 0.0522 - val_mse: 0.0522 - val_mae: 0.2052 - lr: 1.0000e-05 - 73ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0723 - val_loss: 0.0522 - val_mse: 0.0522 - val_mae: 0.2052 - lr: 1.0000e-05 - 75ms/epoch - 4ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0715 - val_loss: 0.0523 - val_mse: 0.0523 - val_mae: 0.2054 - lr: 1.0000e-05 - 76ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.04192
17/17 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0702 - val_loss: 0.0523 - val_mse: 0.0523 - val_mae: 0.2055 - lr: 1.0000e-05 - 73ms/epoch - 4ms/step
Epoch 00060: early stopping

SMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 23.38002191723926 
RMSE:	 4.835289227878645 
MAPE:	 3.8675720673818827

EMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 35.056668726825066 
RMSE:	 5.920867227596399 
MAPE:	 4.704877912816018

WMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 44.87192646385527 
RMSE:	 6.698651092858566 
MAPE:	 5.33068935026581
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.780, Time=2.53 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.33 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15584.877, Time=8.18 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=5.61 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15271.475, Time=7.54 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15128.422, Time=10.03 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16352.675, Time=16.56 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17028.022, Time=5.28 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17002.621, Time=3.19 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17085.445, Time=6.00 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=15.71 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17001.997, Time=3.29 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16996.668, Time=4.26 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 92.506 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.723
Date:                Sun, 12 Dec 2021   AIC                         -17085.445
Time:                        19:12:20   BIC                         -16958.792
Sample:                             0   HQIC                        -17036.805
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1           -2.8e-10   1.36e-20  -2.05e+10      0.000    -2.8e-10    -2.8e-10
x2         -2.817e-10   1.37e-20  -2.06e+10      0.000   -2.82e-10   -2.82e-10
x3         -2.805e-10   1.36e-20  -2.06e+10      0.000    -2.8e-10    -2.8e-10
x4             1.0000   1.37e-20   7.33e+19      0.000       1.000       1.000
x5         -2.598e-10   1.31e-20  -1.98e+10      0.000    -2.6e-10    -2.6e-10
x6         -1.389e-09   2.98e-20  -4.66e+10      0.000   -1.39e-09   -1.39e-09
x7         -2.789e-10   1.36e-20  -2.05e+10      0.000   -2.79e-10   -2.79e-10
x8         -2.761e-10   1.35e-20  -2.04e+10      0.000   -2.76e-10   -2.76e-10
x9         -2.219e-12   3.36e-22   -6.6e+09      0.000   -2.22e-12   -2.22e-12
x10        -1.345e-10   9.37e-21  -1.43e+10      0.000   -1.34e-10   -1.34e-10
x11        -2.899e-10   1.39e-20  -2.09e+10      0.000    -2.9e-10    -2.9e-10
x12        -2.602e-10   1.32e-20  -1.98e+10      0.000    -2.6e-10    -2.6e-10
x13        -2.807e-10   1.36e-20  -2.06e+10      0.000   -2.81e-10   -2.81e-10
x14         -1.87e-09   3.52e-20  -5.31e+10      0.000   -1.87e-09   -1.87e-09
x15        -2.825e-10   1.37e-20  -2.07e+10      0.000   -2.82e-10   -2.82e-10
x16        -8.187e-11   7.33e-21  -1.12e+10      0.000   -8.19e-11   -8.19e-11
x17        -2.441e-10   1.27e-20  -1.92e+10      0.000   -2.44e-10   -2.44e-10
x18        -6.411e-10   2.06e-20  -3.11e+10      0.000   -6.41e-10   -6.41e-10
x19        -2.929e-10   1.39e-20  -2.11e+10      0.000   -2.93e-10   -2.93e-10
x20        -4.339e-10    1.7e-20  -2.56e+10      0.000   -4.34e-10   -4.34e-10
x21        -3.589e-13   2.52e-24  -1.42e+11      0.000   -3.59e-13   -3.59e-13
x22        -1.088e-11   2.36e-24   -4.6e+12      0.000   -1.09e-11   -1.09e-11
ar.L1         -0.4923   1.46e-22  -3.37e+21      0.000      -0.492      -0.492
ar.L2         -0.1923   8.47e-23  -2.27e+21      0.000      -0.192      -0.192
ar.L3         -0.0462   4.02e-23  -1.15e+21      0.000      -0.046      -0.046
ma.L1         -0.7077   3.31e-22  -2.14e+21      0.000      -0.708      -0.708
sigma2       8.99e-11   6.95e-11      1.293      0.196   -4.64e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  55.15   Jarque-Bera (JB):           4171184.78
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.27
Prob(H) (two-sided):                  0.00   Kurtosis:                       355.49
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.53e+42. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 1.15301, saving model to LSTM7.h5
10/10 - 2s - loss: 0.7441 - mse: 0.7441 - mae: 0.7483 - val_loss: 1.1530 - val_mse: 1.1530 - val_mae: 1.0424 - lr: 0.0010 - 2s/epoch - 226ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 1.15301 to 0.75446, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0660 - mse: 0.0660 - mae: 0.2157 - val_loss: 0.7545 - val_mse: 0.7545 - val_mae: 0.8393 - lr: 0.0010 - 74ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.75446 to 0.60415, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0798 - mse: 0.0798 - mae: 0.2423 - val_loss: 0.6041 - val_mse: 0.6041 - val_mae: 0.7490 - lr: 0.0010 - 75ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.60415 to 0.54999, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0518 - mse: 0.0518 - mae: 0.1903 - val_loss: 0.5500 - val_mse: 0.5500 - val_mae: 0.7145 - lr: 0.0010 - 76ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.54999 to 0.49319, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0293 - mse: 0.0293 - mae: 0.1400 - val_loss: 0.4932 - val_mse: 0.4932 - val_mae: 0.6759 - lr: 0.0010 - 73ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.49319 to 0.41422, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0290 - mse: 0.0290 - mae: 0.1384 - val_loss: 0.4142 - val_mse: 0.4142 - val_mae: 0.6180 - lr: 0.0010 - 72ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.41422 to 0.34809, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0240 - mse: 0.0240 - mae: 0.1267 - val_loss: 0.3481 - val_mse: 0.3481 - val_mae: 0.5651 - lr: 0.0010 - 67ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.34809 to 0.30162, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0225 - mse: 0.0225 - mae: 0.1230 - val_loss: 0.3016 - val_mse: 0.3016 - val_mae: 0.5249 - lr: 0.0010 - 88ms/epoch - 9ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.30162 to 0.27254, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0194 - mse: 0.0194 - mae: 0.1148 - val_loss: 0.2725 - val_mse: 0.2725 - val_mae: 0.4983 - lr: 0.0010 - 65ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.27254 to 0.25320, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0173 - mse: 0.0173 - mae: 0.1055 - val_loss: 0.2532 - val_mse: 0.2532 - val_mae: 0.4800 - lr: 0.0010 - 63ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.25320 to 0.24192, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0158 - mse: 0.0158 - mae: 0.1016 - val_loss: 0.2419 - val_mse: 0.2419 - val_mae: 0.4693 - lr: 0.0010 - 68ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.24192 to 0.23391, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0153 - mse: 0.0153 - mae: 0.1009 - val_loss: 0.2339 - val_mse: 0.2339 - val_mae: 0.4617 - lr: 0.0010 - 62ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.23391 to 0.22569, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0132 - mse: 0.0132 - mae: 0.0915 - val_loss: 0.2257 - val_mse: 0.2257 - val_mae: 0.4536 - lr: 0.0010 - 69ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.22569 to 0.21044, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0126 - mse: 0.0126 - mae: 0.0898 - val_loss: 0.2104 - val_mse: 0.2104 - val_mae: 0.4376 - lr: 0.0010 - 70ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.21044 to 0.19835, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0131 - mse: 0.0131 - mae: 0.0921 - val_loss: 0.1984 - val_mse: 0.1984 - val_mae: 0.4245 - lr: 0.0010 - 78ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.19835 to 0.19224, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0114 - mse: 0.0114 - mae: 0.0867 - val_loss: 0.1922 - val_mse: 0.1922 - val_mae: 0.4180 - lr: 0.0010 - 75ms/epoch - 8ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.19224 to 0.18878, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0112 - mse: 0.0112 - mae: 0.0856 - val_loss: 0.1888 - val_mse: 0.1888 - val_mae: 0.4144 - lr: 0.0010 - 80ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.18878 to 0.18213, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0103 - mse: 0.0103 - mae: 0.0811 - val_loss: 0.1821 - val_mse: 0.1821 - val_mae: 0.4069 - lr: 0.0010 - 77ms/epoch - 8ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.18213
10/10 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0804 - val_loss: 0.1826 - val_mse: 0.1826 - val_mae: 0.4077 - lr: 0.0010 - 66ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.18213 to 0.17747, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0093 - mse: 0.0093 - mae: 0.0770 - val_loss: 0.1775 - val_mse: 0.1775 - val_mae: 0.4019 - lr: 0.0010 - 75ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.17747 to 0.17298, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0093 - mse: 0.0093 - mae: 0.0766 - val_loss: 0.1730 - val_mse: 0.1730 - val_mae: 0.3967 - lr: 0.0010 - 74ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss improved from 0.17298 to 0.16400, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0096 - mse: 0.0096 - mae: 0.0780 - val_loss: 0.1640 - val_mse: 0.1640 - val_mae: 0.3859 - lr: 0.0010 - 68ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss improved from 0.16400 to 0.16111, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0725 - val_loss: 0.1611 - val_mse: 0.1611 - val_mae: 0.3823 - lr: 0.0010 - 70ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss improved from 0.16111 to 0.15854, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0084 - mse: 0.0084 - mae: 0.0723 - val_loss: 0.1585 - val_mse: 0.1585 - val_mae: 0.3792 - lr: 0.0010 - 67ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.15854
10/10 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0693 - val_loss: 0.1615 - val_mse: 0.1615 - val_mae: 0.3830 - lr: 0.0010 - 56ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.15854
10/10 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0668 - val_loss: 0.1597 - val_mse: 0.1597 - val_mae: 0.3808 - lr: 0.0010 - 62ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss improved from 0.15854 to 0.15737, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0689 - val_loss: 0.1574 - val_mse: 0.1574 - val_mae: 0.3779 - lr: 0.0010 - 83ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss improved from 0.15737 to 0.15513, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0687 - val_loss: 0.1551 - val_mse: 0.1551 - val_mae: 0.3752 - lr: 0.0010 - 74ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss improved from 0.15513 to 0.14804, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0637 - val_loss: 0.1480 - val_mse: 0.1480 - val_mae: 0.3659 - lr: 0.0010 - 76ms/epoch - 8ms/step
Epoch 30/500

Epoch 00030: val_loss improved from 0.14804 to 0.13703, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0642 - val_loss: 0.1370 - val_mse: 0.1370 - val_mae: 0.3510 - lr: 0.0010 - 95ms/epoch - 9ms/step
Epoch 31/500

Epoch 00031: val_loss improved from 0.13703 to 0.13130, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0634 - val_loss: 0.1313 - val_mse: 0.1313 - val_mae: 0.3430 - lr: 0.0010 - 76ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss improved from 0.13130 to 0.12866, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0639 - val_loss: 0.1287 - val_mse: 0.1287 - val_mae: 0.3392 - lr: 0.0010 - 79ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.12866
10/10 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0625 - val_loss: 0.1394 - val_mse: 0.1394 - val_mae: 0.3540 - lr: 0.0010 - 59ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.12866
10/10 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0651 - val_loss: 0.1404 - val_mse: 0.1404 - val_mae: 0.3553 - lr: 0.0010 - 58ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.12866
10/10 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0654 - val_loss: 0.1350 - val_mse: 0.1350 - val_mae: 0.3479 - lr: 0.0010 - 57ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.12866
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0612 - val_loss: 0.1307 - val_mse: 0.1307 - val_mae: 0.3419 - lr: 0.0010 - 56ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00037: val_loss did not improve from 0.12866
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0613 - val_loss: 0.1295 - val_mse: 0.1295 - val_mae: 0.3401 - lr: 0.0010 - 53ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.12866
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0585 - val_loss: 0.1289 - val_mse: 0.1289 - val_mae: 0.3393 - lr: 1.0000e-04 - 52ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss improved from 0.12866 to 0.12793, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0594 - val_loss: 0.1279 - val_mse: 0.1279 - val_mae: 0.3380 - lr: 1.0000e-04 - 61ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss improved from 0.12793 to 0.12720, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0606 - val_loss: 0.1272 - val_mse: 0.1272 - val_mae: 0.3370 - lr: 1.0000e-04 - 69ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss improved from 0.12720 to 0.12683, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0600 - val_loss: 0.1268 - val_mse: 0.1268 - val_mae: 0.3365 - lr: 1.0000e-04 - 79ms/epoch - 8ms/step
Epoch 42/500

Epoch 00042: val_loss improved from 0.12683 to 0.12659, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0590 - val_loss: 0.1266 - val_mse: 0.1266 - val_mae: 0.3361 - lr: 1.0000e-04 - 81ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss improved from 0.12659 to 0.12608, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0614 - val_loss: 0.1261 - val_mse: 0.1261 - val_mae: 0.3354 - lr: 1.0000e-04 - 76ms/epoch - 8ms/step
Epoch 44/500

Epoch 00044: val_loss improved from 0.12608 to 0.12588, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0606 - val_loss: 0.1259 - val_mse: 0.1259 - val_mae: 0.3351 - lr: 1.0000e-04 - 75ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss improved from 0.12588 to 0.12583, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0601 - val_loss: 0.1258 - val_mse: 0.1258 - val_mae: 0.3351 - lr: 1.0000e-04 - 71ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0591 - val_loss: 0.1262 - val_mse: 0.1262 - val_mae: 0.3356 - lr: 1.0000e-04 - 63ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0621 - val_loss: 0.1263 - val_mse: 0.1263 - val_mae: 0.3357 - lr: 1.0000e-04 - 58ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0598 - val_loss: 0.1263 - val_mse: 0.1263 - val_mae: 0.3357 - lr: 1.0000e-04 - 56ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00049: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0600 - val_loss: 0.1262 - val_mse: 0.1262 - val_mae: 0.3356 - lr: 1.0000e-04 - 53ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0571 - val_loss: 0.1263 - val_mse: 0.1263 - val_mae: 0.3357 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0587 - val_loss: 0.1263 - val_mse: 0.1263 - val_mae: 0.3357 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0597 - val_loss: 0.1262 - val_mse: 0.1262 - val_mae: 0.3356 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0583 - val_loss: 0.1261 - val_mse: 0.1261 - val_mae: 0.3354 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 54/500

Epoch 00054: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00054: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0576 - val_loss: 0.1261 - val_mse: 0.1261 - val_mae: 0.3354 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0592 - val_loss: 0.1261 - val_mse: 0.1261 - val_mae: 0.3354 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0568 - val_loss: 0.1260 - val_mse: 0.1260 - val_mae: 0.3353 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0587 - val_loss: 0.1259 - val_mse: 0.1259 - val_mae: 0.3352 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0604 - val_loss: 0.1259 - val_mse: 0.1259 - val_mae: 0.3352 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0601 - val_loss: 0.1259 - val_mse: 0.1259 - val_mae: 0.3351 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0594 - val_loss: 0.1258 - val_mse: 0.1258 - val_mae: 0.3351 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0602 - val_loss: 0.1259 - val_mse: 0.1259 - val_mae: 0.3352 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0585 - val_loss: 0.1260 - val_mse: 0.1260 - val_mae: 0.3353 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0594 - val_loss: 0.1260 - val_mse: 0.1260 - val_mae: 0.3352 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.12583
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0588 - val_loss: 0.1258 - val_mse: 0.1258 - val_mae: 0.3351 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss improved from 0.12583 to 0.12572, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0618 - val_loss: 0.1257 - val_mse: 0.1257 - val_mae: 0.3349 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 66/500

Epoch 00066: val_loss improved from 0.12572 to 0.12559, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0569 - val_loss: 0.1256 - val_mse: 0.1256 - val_mae: 0.3347 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.12559
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0568 - val_loss: 0.1256 - val_mse: 0.1256 - val_mae: 0.3347 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.12559
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.1256 - val_mse: 0.1256 - val_mae: 0.3347 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 69/500

Epoch 00069: val_loss improved from 0.12559 to 0.12556, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.1256 - val_mse: 0.1256 - val_mae: 0.3347 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 70/500

Epoch 00070: val_loss improved from 0.12556 to 0.12552, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0595 - val_loss: 0.1255 - val_mse: 0.1255 - val_mae: 0.3346 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 71/500

Epoch 00071: val_loss improved from 0.12552 to 0.12539, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.1254 - val_mse: 0.1254 - val_mae: 0.3344 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 72/500

Epoch 00072: val_loss improved from 0.12539 to 0.12536, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0599 - val_loss: 0.1254 - val_mse: 0.1254 - val_mae: 0.3344 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 73/500

Epoch 00073: val_loss improved from 0.12536 to 0.12535, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0585 - val_loss: 0.1253 - val_mse: 0.1253 - val_mae: 0.3344 - lr: 1.0000e-05 - 75ms/epoch - 8ms/step
Epoch 74/500

Epoch 00074: val_loss improved from 0.12535 to 0.12531, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0598 - val_loss: 0.1253 - val_mse: 0.1253 - val_mae: 0.3343 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 75/500

Epoch 00075: val_loss improved from 0.12531 to 0.12527, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0564 - val_loss: 0.1253 - val_mse: 0.1253 - val_mae: 0.3342 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0595 - val_loss: 0.1254 - val_mse: 0.1254 - val_mae: 0.3344 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0562 - val_loss: 0.1255 - val_mse: 0.1255 - val_mae: 0.3346 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0588 - val_loss: 0.1257 - val_mse: 0.1257 - val_mae: 0.3348 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0572 - val_loss: 0.1257 - val_mse: 0.1257 - val_mae: 0.3349 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0603 - val_loss: 0.1257 - val_mse: 0.1257 - val_mae: 0.3349 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0609 - val_loss: 0.1256 - val_mse: 0.1256 - val_mae: 0.3347 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0585 - val_loss: 0.1256 - val_mse: 0.1256 - val_mae: 0.3347 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0567 - val_loss: 0.1256 - val_mse: 0.1256 - val_mae: 0.3347 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 84/500

Epoch 00084: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0588 - val_loss: 0.1255 - val_mse: 0.1255 - val_mae: 0.3346 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 85/500

Epoch 00085: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0571 - val_loss: 0.1256 - val_mse: 0.1256 - val_mae: 0.3347 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 86/500

Epoch 00086: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0596 - val_loss: 0.1255 - val_mse: 0.1255 - val_mae: 0.3346 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 87/500

Epoch 00087: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0590 - val_loss: 0.1254 - val_mse: 0.1254 - val_mae: 0.3345 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 88/500

Epoch 00088: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0607 - val_loss: 0.1254 - val_mse: 0.1254 - val_mae: 0.3345 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 89/500

Epoch 00089: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0584 - val_loss: 0.1254 - val_mse: 0.1254 - val_mae: 0.3344 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 90/500

Epoch 00090: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0607 - val_loss: 0.1253 - val_mse: 0.1253 - val_mae: 0.3343 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 91/500

Epoch 00091: val_loss did not improve from 0.12527
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.1253 - val_mse: 0.1253 - val_mae: 0.3343 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 92/500

Epoch 00092: val_loss improved from 0.12527 to 0.12522, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0601 - val_loss: 0.1252 - val_mse: 0.1252 - val_mae: 0.3342 - lr: 1.0000e-05 - 92ms/epoch - 9ms/step
Epoch 93/500

Epoch 00093: val_loss improved from 0.12522 to 0.12509, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0618 - val_loss: 0.1251 - val_mse: 0.1251 - val_mae: 0.3340 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 94/500

Epoch 00094: val_loss improved from 0.12509 to 0.12495, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0570 - val_loss: 0.1250 - val_mse: 0.1250 - val_mae: 0.3338 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 95/500

Epoch 00095: val_loss improved from 0.12495 to 0.12486, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0588 - val_loss: 0.1249 - val_mse: 0.1249 - val_mae: 0.3337 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 96/500

Epoch 00096: val_loss did not improve from 0.12486
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0589 - val_loss: 0.1249 - val_mse: 0.1249 - val_mae: 0.3337 - lr: 1.0000e-05 - 49ms/epoch - 5ms/step
Epoch 97/500

Epoch 00097: val_loss did not improve from 0.12486
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0578 - val_loss: 0.1249 - val_mse: 0.1249 - val_mae: 0.3338 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 98/500

Epoch 00098: val_loss did not improve from 0.12486
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0587 - val_loss: 0.1249 - val_mse: 0.1249 - val_mae: 0.3337 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 99/500

Epoch 00099: val_loss did not improve from 0.12486
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0592 - val_loss: 0.1249 - val_mse: 0.1249 - val_mae: 0.3337 - lr: 1.0000e-05 - 50ms/epoch - 5ms/step
Epoch 100/500

Epoch 00100: val_loss improved from 0.12486 to 0.12483, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0570 - val_loss: 0.1248 - val_mse: 0.1248 - val_mae: 0.3336 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 101/500

Epoch 00101: val_loss improved from 0.12483 to 0.12476, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0583 - val_loss: 0.1248 - val_mse: 0.1248 - val_mae: 0.3335 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 102/500

Epoch 00102: val_loss improved from 0.12476 to 0.12466, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0588 - val_loss: 0.1247 - val_mse: 0.1247 - val_mae: 0.3334 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 103/500

Epoch 00103: val_loss improved from 0.12466 to 0.12464, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0610 - val_loss: 0.1246 - val_mse: 0.1246 - val_mae: 0.3334 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 104/500

Epoch 00104: val_loss did not improve from 0.12464
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0574 - val_loss: 0.1247 - val_mse: 0.1247 - val_mae: 0.3335 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 105/500

Epoch 00105: val_loss did not improve from 0.12464
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0588 - val_loss: 0.1246 - val_mse: 0.1246 - val_mae: 0.3334 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 106/500

Epoch 00106: val_loss did not improve from 0.12464
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0591 - val_loss: 0.1247 - val_mse: 0.1247 - val_mae: 0.3334 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 107/500

Epoch 00107: val_loss improved from 0.12464 to 0.12459, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0601 - val_loss: 0.1246 - val_mse: 0.1246 - val_mae: 0.3333 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 108/500

Epoch 00108: val_loss improved from 0.12459 to 0.12445, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0604 - val_loss: 0.1245 - val_mse: 0.1245 - val_mae: 0.3331 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 109/500

Epoch 00109: val_loss improved from 0.12445 to 0.12443, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0602 - val_loss: 0.1244 - val_mse: 0.1244 - val_mae: 0.3330 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 110/500

Epoch 00110: val_loss improved from 0.12443 to 0.12439, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0580 - val_loss: 0.1244 - val_mse: 0.1244 - val_mae: 0.3330 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 111/500

Epoch 00111: val_loss improved from 0.12439 to 0.12433, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0580 - val_loss: 0.1243 - val_mse: 0.1243 - val_mae: 0.3329 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 112/500

Epoch 00112: val_loss improved from 0.12433 to 0.12424, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0593 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3328 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 113/500

Epoch 00113: val_loss improved from 0.12424 to 0.12417, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0579 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3327 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 114/500

Epoch 00114: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3327 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 115/500

Epoch 00115: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0580 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3327 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 116/500

Epoch 00116: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0554 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3328 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 117/500

Epoch 00117: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0574 - val_loss: 0.1243 - val_mse: 0.1243 - val_mae: 0.3329 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 118/500

Epoch 00118: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0605 - val_loss: 0.1243 - val_mse: 0.1243 - val_mae: 0.3329 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 119/500

Epoch 00119: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0581 - val_loss: 0.1245 - val_mse: 0.1245 - val_mae: 0.3331 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 120/500

Epoch 00120: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0569 - val_loss: 0.1246 - val_mse: 0.1246 - val_mae: 0.3332 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 121/500

Epoch 00121: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0591 - val_loss: 0.1246 - val_mse: 0.1246 - val_mae: 0.3332 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 122/500

Epoch 00122: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0570 - val_loss: 0.1244 - val_mse: 0.1244 - val_mae: 0.3330 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 123/500

Epoch 00123: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0576 - val_loss: 0.1244 - val_mse: 0.1244 - val_mae: 0.3331 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 124/500

Epoch 00124: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0595 - val_loss: 0.1244 - val_mse: 0.1244 - val_mae: 0.3330 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 125/500

Epoch 00125: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0581 - val_loss: 0.1243 - val_mse: 0.1243 - val_mae: 0.3328 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 126/500

Epoch 00126: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0597 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3327 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 127/500

Epoch 00127: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0623 - val_loss: 0.1243 - val_mse: 0.1243 - val_mae: 0.3329 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 128/500

Epoch 00128: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0585 - val_loss: 0.1244 - val_mse: 0.1244 - val_mae: 0.3330 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 129/500

Epoch 00129: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0594 - val_loss: 0.1244 - val_mse: 0.1244 - val_mae: 0.3330 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 130/500

Epoch 00130: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0585 - val_loss: 0.1243 - val_mse: 0.1243 - val_mae: 0.3329 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 131/500

Epoch 00131: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3328 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 132/500

Epoch 00132: val_loss did not improve from 0.12417
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3328 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 133/500

Epoch 00133: val_loss improved from 0.12417 to 0.12407, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0568 - val_loss: 0.1241 - val_mse: 0.1241 - val_mae: 0.3326 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 134/500

Epoch 00134: val_loss improved from 0.12407 to 0.12394, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.1239 - val_mse: 0.1239 - val_mae: 0.3324 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 135/500

Epoch 00135: val_loss improved from 0.12394 to 0.12385, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0541 - val_loss: 0.1239 - val_mse: 0.1239 - val_mae: 0.3322 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 136/500

Epoch 00136: val_loss improved from 0.12385 to 0.12374, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0568 - val_loss: 0.1237 - val_mse: 0.1237 - val_mae: 0.3321 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 137/500

Epoch 00137: val_loss improved from 0.12374 to 0.12370, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0592 - val_loss: 0.1237 - val_mse: 0.1237 - val_mae: 0.3320 - lr: 1.0000e-05 - 94ms/epoch - 9ms/step
Epoch 138/500

Epoch 00138: val_loss improved from 0.12370 to 0.12370, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0591 - val_loss: 0.1237 - val_mse: 0.1237 - val_mae: 0.3320 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 139/500

Epoch 00139: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0572 - val_loss: 0.1237 - val_mse: 0.1237 - val_mae: 0.3320 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 140/500

Epoch 00140: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.1238 - val_mse: 0.1238 - val_mae: 0.3321 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 141/500

Epoch 00141: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0588 - val_loss: 0.1238 - val_mse: 0.1238 - val_mae: 0.3321 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 142/500

Epoch 00142: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0563 - val_loss: 0.1239 - val_mse: 0.1239 - val_mae: 0.3323 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 143/500

Epoch 00143: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0582 - val_loss: 0.1238 - val_mse: 0.1238 - val_mae: 0.3322 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 144/500

Epoch 00144: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0622 - val_loss: 0.1238 - val_mse: 0.1238 - val_mae: 0.3321 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 145/500

Epoch 00145: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0601 - val_loss: 0.1238 - val_mse: 0.1238 - val_mae: 0.3322 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 146/500

Epoch 00146: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0592 - val_loss: 0.1239 - val_mse: 0.1239 - val_mae: 0.3323 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 147/500

Epoch 00147: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.1240 - val_mse: 0.1240 - val_mae: 0.3324 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 148/500

Epoch 00148: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0563 - val_loss: 0.1239 - val_mse: 0.1239 - val_mae: 0.3323 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 149/500

Epoch 00149: val_loss did not improve from 0.12370
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0564 - val_loss: 0.1238 - val_mse: 0.1238 - val_mae: 0.3321 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 150/500

Epoch 00150: val_loss improved from 0.12370 to 0.12368, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0586 - val_loss: 0.1237 - val_mse: 0.1237 - val_mae: 0.3320 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 151/500

Epoch 00151: val_loss improved from 0.12368 to 0.12361, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0567 - val_loss: 0.1236 - val_mse: 0.1236 - val_mae: 0.3319 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 152/500

Epoch 00152: val_loss improved from 0.12361 to 0.12361, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0577 - val_loss: 0.1236 - val_mse: 0.1236 - val_mae: 0.3319 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 153/500

Epoch 00153: val_loss improved from 0.12361 to 0.12350, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0590 - val_loss: 0.1235 - val_mse: 0.1235 - val_mae: 0.3317 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 154/500

Epoch 00154: val_loss improved from 0.12350 to 0.12342, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0596 - val_loss: 0.1234 - val_mse: 0.1234 - val_mae: 0.3316 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 155/500

Epoch 00155: val_loss did not improve from 0.12342
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0586 - val_loss: 0.1236 - val_mse: 0.1236 - val_mae: 0.3319 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 156/500

Epoch 00156: val_loss did not improve from 0.12342
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0581 - val_loss: 0.1236 - val_mse: 0.1236 - val_mae: 0.3318 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 157/500

Epoch 00157: val_loss improved from 0.12342 to 0.12331, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0583 - val_loss: 0.1233 - val_mse: 0.1233 - val_mae: 0.3315 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 158/500

Epoch 00158: val_loss improved from 0.12331 to 0.12310, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0615 - val_loss: 0.1231 - val_mse: 0.1231 - val_mae: 0.3312 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 159/500

Epoch 00159: val_loss did not improve from 0.12310
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0553 - val_loss: 0.1232 - val_mse: 0.1232 - val_mae: 0.3313 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 160/500

Epoch 00160: val_loss did not improve from 0.12310
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0573 - val_loss: 0.1233 - val_mse: 0.1233 - val_mae: 0.3314 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 161/500

Epoch 00161: val_loss did not improve from 0.12310
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0590 - val_loss: 0.1232 - val_mse: 0.1232 - val_mae: 0.3314 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 162/500

Epoch 00162: val_loss did not improve from 0.12310
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0597 - val_loss: 0.1233 - val_mse: 0.1233 - val_mae: 0.3315 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 163/500

Epoch 00163: val_loss did not improve from 0.12310
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.1232 - val_mse: 0.1232 - val_mae: 0.3313 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 164/500

Epoch 00164: val_loss did not improve from 0.12310
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0594 - val_loss: 0.1232 - val_mse: 0.1232 - val_mae: 0.3313 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 165/500

Epoch 00165: val_loss improved from 0.12310 to 0.12306, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.1231 - val_mse: 0.1231 - val_mae: 0.3311 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 166/500

Epoch 00166: val_loss improved from 0.12306 to 0.12301, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0595 - val_loss: 0.1230 - val_mse: 0.1230 - val_mae: 0.3310 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 167/500

Epoch 00167: val_loss improved from 0.12301 to 0.12298, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0589 - val_loss: 0.1230 - val_mse: 0.1230 - val_mae: 0.3310 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 168/500

Epoch 00168: val_loss did not improve from 0.12298
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0559 - val_loss: 0.1231 - val_mse: 0.1231 - val_mae: 0.3312 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 169/500

Epoch 00169: val_loss did not improve from 0.12298
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0576 - val_loss: 0.1231 - val_mse: 0.1231 - val_mae: 0.3311 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 170/500

Epoch 00170: val_loss improved from 0.12298 to 0.12291, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0554 - val_loss: 0.1229 - val_mse: 0.1229 - val_mae: 0.3309 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 171/500

Epoch 00171: val_loss did not improve from 0.12291
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0590 - val_loss: 0.1229 - val_mse: 0.1229 - val_mae: 0.3309 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 172/500

Epoch 00172: val_loss did not improve from 0.12291
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0569 - val_loss: 0.1231 - val_mse: 0.1231 - val_mae: 0.3311 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 173/500

Epoch 00173: val_loss did not improve from 0.12291
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0585 - val_loss: 0.1231 - val_mse: 0.1231 - val_mae: 0.3312 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 174/500

Epoch 00174: val_loss did not improve from 0.12291
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0586 - val_loss: 0.1232 - val_mse: 0.1232 - val_mae: 0.3313 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 175/500

Epoch 00175: val_loss did not improve from 0.12291
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0587 - val_loss: 0.1230 - val_mse: 0.1230 - val_mae: 0.3310 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 176/500

Epoch 00176: val_loss improved from 0.12291 to 0.12278, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0582 - val_loss: 0.1228 - val_mse: 0.1228 - val_mae: 0.3307 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 177/500

Epoch 00177: val_loss improved from 0.12278 to 0.12254, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0603 - val_loss: 0.1225 - val_mse: 0.1225 - val_mae: 0.3304 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 178/500

Epoch 00178: val_loss improved from 0.12254 to 0.12232, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0551 - val_loss: 0.1223 - val_mse: 0.1223 - val_mae: 0.3300 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 179/500

Epoch 00179: val_loss improved from 0.12232 to 0.12218, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0582 - val_loss: 0.1222 - val_mse: 0.1222 - val_mae: 0.3298 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 180/500

Epoch 00180: val_loss improved from 0.12218 to 0.12212, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0579 - val_loss: 0.1221 - val_mse: 0.1221 - val_mae: 0.3297 - lr: 1.0000e-05 - 75ms/epoch - 8ms/step
Epoch 181/500

Epoch 00181: val_loss improved from 0.12212 to 0.12207, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0561 - val_loss: 0.1221 - val_mse: 0.1221 - val_mae: 0.3297 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 182/500

Epoch 00182: val_loss improved from 0.12207 to 0.12206, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0586 - val_loss: 0.1221 - val_mse: 0.1221 - val_mae: 0.3297 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 183/500

Epoch 00183: val_loss did not improve from 0.12206
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0579 - val_loss: 0.1221 - val_mse: 0.1221 - val_mae: 0.3297 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 184/500

Epoch 00184: val_loss did not improve from 0.12206
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0591 - val_loss: 0.1223 - val_mse: 0.1223 - val_mae: 0.3301 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 185/500

Epoch 00185: val_loss did not improve from 0.12206
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0594 - val_loss: 0.1223 - val_mse: 0.1223 - val_mae: 0.3301 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 186/500

Epoch 00186: val_loss did not improve from 0.12206
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0588 - val_loss: 0.1222 - val_mse: 0.1222 - val_mae: 0.3299 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 187/500

Epoch 00187: val_loss did not improve from 0.12206
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.1221 - val_mse: 0.1221 - val_mae: 0.3297 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 188/500

Epoch 00188: val_loss improved from 0.12206 to 0.12187, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0570 - val_loss: 0.1219 - val_mse: 0.1219 - val_mae: 0.3294 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 189/500

Epoch 00189: val_loss improved from 0.12187 to 0.12157, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.1216 - val_mse: 0.1216 - val_mae: 0.3290 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 190/500

Epoch 00190: val_loss improved from 0.12157 to 0.12142, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0594 - val_loss: 0.1214 - val_mse: 0.1214 - val_mae: 0.3287 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 191/500

Epoch 00191: val_loss improved from 0.12142 to 0.12137, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0586 - val_loss: 0.1214 - val_mse: 0.1214 - val_mae: 0.3287 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 192/500

Epoch 00192: val_loss did not improve from 0.12137
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0571 - val_loss: 0.1214 - val_mse: 0.1214 - val_mae: 0.3287 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 193/500

Epoch 00193: val_loss did not improve from 0.12137
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0580 - val_loss: 0.1215 - val_mse: 0.1215 - val_mae: 0.3288 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 194/500

Epoch 00194: val_loss did not improve from 0.12137
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0552 - val_loss: 0.1216 - val_mse: 0.1216 - val_mae: 0.3290 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 195/500

Epoch 00195: val_loss did not improve from 0.12137
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0620 - val_loss: 0.1217 - val_mse: 0.1217 - val_mae: 0.3291 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 196/500

Epoch 00196: val_loss did not improve from 0.12137
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0578 - val_loss: 0.1216 - val_mse: 0.1216 - val_mae: 0.3290 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 197/500

Epoch 00197: val_loss did not improve from 0.12137
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0580 - val_loss: 0.1214 - val_mse: 0.1214 - val_mae: 0.3288 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 198/500

Epoch 00198: val_loss improved from 0.12137 to 0.12123, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0595 - val_loss: 0.1212 - val_mse: 0.1212 - val_mae: 0.3285 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 199/500

Epoch 00199: val_loss did not improve from 0.12123
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.1213 - val_mse: 0.1213 - val_mae: 0.3286 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 200/500

Epoch 00200: val_loss improved from 0.12123 to 0.12120, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0570 - val_loss: 0.1212 - val_mse: 0.1212 - val_mae: 0.3284 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 201/500

Epoch 00201: val_loss improved from 0.12120 to 0.12105, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0568 - val_loss: 0.1210 - val_mse: 0.1210 - val_mae: 0.3282 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 202/500

Epoch 00202: val_loss improved from 0.12105 to 0.12095, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0576 - val_loss: 0.1210 - val_mse: 0.1210 - val_mae: 0.3281 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 203/500

Epoch 00203: val_loss improved from 0.12095 to 0.12078, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0569 - val_loss: 0.1208 - val_mse: 0.1208 - val_mae: 0.3278 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 204/500

Epoch 00204: val_loss improved from 0.12078 to 0.12059, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0601 - val_loss: 0.1206 - val_mse: 0.1206 - val_mae: 0.3275 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 205/500

Epoch 00205: val_loss improved from 0.12059 to 0.12034, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0575 - val_loss: 0.1203 - val_mse: 0.1203 - val_mae: 0.3272 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 206/500

Epoch 00206: val_loss improved from 0.12034 to 0.12019, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0580 - val_loss: 0.1202 - val_mse: 0.1202 - val_mae: 0.3270 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 207/500

Epoch 00207: val_loss improved from 0.12019 to 0.12009, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0559 - val_loss: 0.1201 - val_mse: 0.1201 - val_mae: 0.3268 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 208/500

Epoch 00208: val_loss did not improve from 0.12009
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0577 - val_loss: 0.1203 - val_mse: 0.1203 - val_mae: 0.3272 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 209/500

Epoch 00209: val_loss did not improve from 0.12009
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0576 - val_loss: 0.1205 - val_mse: 0.1205 - val_mae: 0.3274 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 210/500

Epoch 00210: val_loss did not improve from 0.12009
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0578 - val_loss: 0.1204 - val_mse: 0.1204 - val_mae: 0.3273 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 211/500

Epoch 00211: val_loss did not improve from 0.12009
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0570 - val_loss: 0.1202 - val_mse: 0.1202 - val_mae: 0.3270 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 212/500

Epoch 00212: val_loss did not improve from 0.12009
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.1202 - val_mse: 0.1202 - val_mae: 0.3270 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 213/500

Epoch 00213: val_loss did not improve from 0.12009
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0573 - val_loss: 0.1202 - val_mse: 0.1202 - val_mae: 0.3269 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 214/500

Epoch 00214: val_loss improved from 0.12009 to 0.12006, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.1201 - val_mse: 0.1201 - val_mae: 0.3268 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 215/500

Epoch 00215: val_loss improved from 0.12006 to 0.11989, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0562 - val_loss: 0.1199 - val_mse: 0.1199 - val_mae: 0.3265 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 216/500

Epoch 00216: val_loss improved from 0.11989 to 0.11976, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0584 - val_loss: 0.1198 - val_mse: 0.1198 - val_mae: 0.3264 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 217/500

Epoch 00217: val_loss improved from 0.11976 to 0.11955, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0584 - val_loss: 0.1196 - val_mse: 0.1196 - val_mae: 0.3260 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 218/500

Epoch 00218: val_loss improved from 0.11955 to 0.11942, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0572 - val_loss: 0.1194 - val_mse: 0.1194 - val_mae: 0.3259 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 219/500

Epoch 00219: val_loss improved from 0.11942 to 0.11933, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0555 - val_loss: 0.1193 - val_mse: 0.1193 - val_mae: 0.3257 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 220/500

Epoch 00220: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.1193 - val_mse: 0.1193 - val_mae: 0.3258 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 221/500

Epoch 00221: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0567 - val_loss: 0.1194 - val_mse: 0.1194 - val_mae: 0.3259 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 222/500

Epoch 00222: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0583 - val_loss: 0.1196 - val_mse: 0.1196 - val_mae: 0.3262 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 223/500

Epoch 00223: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0577 - val_loss: 0.1198 - val_mse: 0.1198 - val_mae: 0.3265 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 224/500

Epoch 00224: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0576 - val_loss: 0.1200 - val_mse: 0.1200 - val_mae: 0.3267 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 225/500

Epoch 00225: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0574 - val_loss: 0.1200 - val_mse: 0.1200 - val_mae: 0.3267 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 226/500

Epoch 00226: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0572 - val_loss: 0.1198 - val_mse: 0.1198 - val_mae: 0.3265 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 227/500

Epoch 00227: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0573 - val_loss: 0.1201 - val_mse: 0.1201 - val_mae: 0.3269 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 228/500

Epoch 00228: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0574 - val_loss: 0.1205 - val_mse: 0.1205 - val_mae: 0.3275 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 229/500

Epoch 00229: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0595 - val_loss: 0.1205 - val_mse: 0.1205 - val_mae: 0.3275 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 230/500

Epoch 00230: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.1204 - val_mse: 0.1204 - val_mae: 0.3273 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 231/500

Epoch 00231: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0582 - val_loss: 0.1204 - val_mse: 0.1204 - val_mae: 0.3273 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 232/500

Epoch 00232: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0603 - val_loss: 0.1203 - val_mse: 0.1203 - val_mae: 0.3272 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 233/500

Epoch 00233: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0589 - val_loss: 0.1205 - val_mse: 0.1205 - val_mae: 0.3274 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 234/500

Epoch 00234: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0594 - val_loss: 0.1207 - val_mse: 0.1207 - val_mae: 0.3278 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 235/500

Epoch 00235: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0581 - val_loss: 0.1207 - val_mse: 0.1207 - val_mae: 0.3277 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 236/500

Epoch 00236: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0546 - val_loss: 0.1207 - val_mse: 0.1207 - val_mae: 0.3277 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 237/500

Epoch 00237: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0585 - val_loss: 0.1203 - val_mse: 0.1203 - val_mae: 0.3271 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 238/500

Epoch 00238: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0575 - val_loss: 0.1200 - val_mse: 0.1200 - val_mae: 0.3268 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 239/500

Epoch 00239: val_loss did not improve from 0.11933
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0542 - val_loss: 0.1196 - val_mse: 0.1196 - val_mae: 0.3261 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 240/500

Epoch 00240: val_loss improved from 0.11933 to 0.11929, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0574 - val_loss: 0.1193 - val_mse: 0.1193 - val_mae: 0.3257 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 241/500

Epoch 00241: val_loss did not improve from 0.11929
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0589 - val_loss: 0.1193 - val_mse: 0.1193 - val_mae: 0.3257 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 242/500

Epoch 00242: val_loss did not improve from 0.11929
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0575 - val_loss: 0.1195 - val_mse: 0.1195 - val_mae: 0.3260 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 243/500

Epoch 00243: val_loss did not improve from 0.11929
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0594 - val_loss: 0.1196 - val_mse: 0.1196 - val_mae: 0.3261 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 244/500

Epoch 00244: val_loss did not improve from 0.11929
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0560 - val_loss: 0.1196 - val_mse: 0.1196 - val_mae: 0.3262 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 245/500

Epoch 00245: val_loss did not improve from 0.11929
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0560 - val_loss: 0.1193 - val_mse: 0.1193 - val_mae: 0.3258 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 246/500

Epoch 00246: val_loss improved from 0.11929 to 0.11925, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0554 - val_loss: 0.1192 - val_mse: 0.1192 - val_mae: 0.3256 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 247/500

Epoch 00247: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0569 - val_loss: 0.1194 - val_mse: 0.1194 - val_mae: 0.3259 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 248/500

Epoch 00248: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0589 - val_loss: 0.1195 - val_mse: 0.1195 - val_mae: 0.3260 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 249/500

Epoch 00249: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0541 - val_loss: 0.1196 - val_mse: 0.1196 - val_mae: 0.3262 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 250/500

Epoch 00250: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0580 - val_loss: 0.1198 - val_mse: 0.1198 - val_mae: 0.3265 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 251/500

Epoch 00251: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0563 - val_loss: 0.1199 - val_mse: 0.1199 - val_mae: 0.3266 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 252/500

Epoch 00252: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0569 - val_loss: 0.1200 - val_mse: 0.1200 - val_mae: 0.3267 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 253/500

Epoch 00253: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0589 - val_loss: 0.1201 - val_mse: 0.1201 - val_mae: 0.3268 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 254/500

Epoch 00254: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0576 - val_loss: 0.1203 - val_mse: 0.1203 - val_mae: 0.3271 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 255/500

Epoch 00255: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0593 - val_loss: 0.1205 - val_mse: 0.1205 - val_mae: 0.3274 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 256/500

Epoch 00256: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0574 - val_loss: 0.1207 - val_mse: 0.1207 - val_mae: 0.3277 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 257/500

Epoch 00257: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0571 - val_loss: 0.1207 - val_mse: 0.1207 - val_mae: 0.3277 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 258/500

Epoch 00258: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0563 - val_loss: 0.1205 - val_mse: 0.1205 - val_mae: 0.3274 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 259/500

Epoch 00259: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0573 - val_loss: 0.1203 - val_mse: 0.1203 - val_mae: 0.3271 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 260/500

Epoch 00260: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0564 - val_loss: 0.1201 - val_mse: 0.1201 - val_mae: 0.3268 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 261/500

Epoch 00261: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0559 - val_loss: 0.1202 - val_mse: 0.1202 - val_mae: 0.3270 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 262/500

Epoch 00262: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0569 - val_loss: 0.1204 - val_mse: 0.1204 - val_mae: 0.3274 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 263/500

Epoch 00263: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0578 - val_loss: 0.1204 - val_mse: 0.1204 - val_mae: 0.3274 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 264/500

Epoch 00264: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0590 - val_loss: 0.1204 - val_mse: 0.1204 - val_mae: 0.3273 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 265/500

Epoch 00265: val_loss did not improve from 0.11925
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0583 - val_loss: 0.1199 - val_mse: 0.1199 - val_mae: 0.3265 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 266/500

Epoch 00266: val_loss improved from 0.11925 to 0.11918, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0572 - val_loss: 0.1192 - val_mse: 0.1192 - val_mae: 0.3255 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 267/500

Epoch 00267: val_loss improved from 0.11918 to 0.11889, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0594 - val_loss: 0.1189 - val_mse: 0.1189 - val_mae: 0.3251 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 268/500

Epoch 00268: val_loss improved from 0.11889 to 0.11851, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.1185 - val_mse: 0.1185 - val_mae: 0.3246 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 269/500

Epoch 00269: val_loss improved from 0.11851 to 0.11827, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0580 - val_loss: 0.1183 - val_mse: 0.1183 - val_mae: 0.3242 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 270/500

Epoch 00270: val_loss improved from 0.11827 to 0.11819, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0582 - val_loss: 0.1182 - val_mse: 0.1182 - val_mae: 0.3241 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 271/500

Epoch 00271: val_loss improved from 0.11819 to 0.11806, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.1181 - val_mse: 0.1181 - val_mae: 0.3239 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 272/500

Epoch 00272: val_loss improved from 0.11806 to 0.11805, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0578 - val_loss: 0.1180 - val_mse: 0.1180 - val_mae: 0.3239 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 273/500

Epoch 00273: val_loss improved from 0.11805 to 0.11790, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0584 - val_loss: 0.1179 - val_mse: 0.1179 - val_mae: 0.3237 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 274/500

Epoch 00274: val_loss did not improve from 0.11790
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.1179 - val_mse: 0.1179 - val_mae: 0.3237 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 275/500

Epoch 00275: val_loss improved from 0.11790 to 0.11789, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0553 - val_loss: 0.1179 - val_mse: 0.1179 - val_mae: 0.3237 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 276/500

Epoch 00276: val_loss did not improve from 0.11789
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0575 - val_loss: 0.1180 - val_mse: 0.1180 - val_mae: 0.3239 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 277/500

Epoch 00277: val_loss did not improve from 0.11789
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0577 - val_loss: 0.1181 - val_mse: 0.1181 - val_mae: 0.3240 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 278/500

Epoch 00278: val_loss did not improve from 0.11789
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0562 - val_loss: 0.1182 - val_mse: 0.1182 - val_mae: 0.3241 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 279/500

Epoch 00279: val_loss did not improve from 0.11789
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0555 - val_loss: 0.1181 - val_mse: 0.1181 - val_mae: 0.3239 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 280/500

Epoch 00280: val_loss did not improve from 0.11789
10/10 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0593 - val_loss: 0.1181 - val_mse: 0.1181 - val_mae: 0.3240 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 281/500

Epoch 00281: val_loss improved from 0.11789 to 0.11788, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.1179 - val_mse: 0.1179 - val_mae: 0.3237 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 282/500

Epoch 00282: val_loss improved from 0.11788 to 0.11768, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0560 - val_loss: 0.1177 - val_mse: 0.1177 - val_mae: 0.3234 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 283/500

Epoch 00283: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0579 - val_loss: 0.1178 - val_mse: 0.1178 - val_mae: 0.3236 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 284/500

Epoch 00284: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0577 - val_loss: 0.1182 - val_mse: 0.1182 - val_mae: 0.3241 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 285/500

Epoch 00285: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0562 - val_loss: 0.1182 - val_mse: 0.1182 - val_mae: 0.3242 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 286/500

Epoch 00286: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0575 - val_loss: 0.1183 - val_mse: 0.1183 - val_mae: 0.3243 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 287/500

Epoch 00287: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0544 - val_loss: 0.1185 - val_mse: 0.1185 - val_mae: 0.3246 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 288/500

Epoch 00288: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0558 - val_loss: 0.1186 - val_mse: 0.1186 - val_mae: 0.3247 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 289/500

Epoch 00289: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0565 - val_loss: 0.1187 - val_mse: 0.1187 - val_mae: 0.3249 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 290/500

Epoch 00290: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.1187 - val_mse: 0.1187 - val_mae: 0.3248 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 291/500

Epoch 00291: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0557 - val_loss: 0.1186 - val_mse: 0.1186 - val_mae: 0.3248 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 292/500

Epoch 00292: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0568 - val_loss: 0.1183 - val_mse: 0.1183 - val_mae: 0.3243 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 293/500

Epoch 00293: val_loss did not improve from 0.11768
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0573 - val_loss: 0.1179 - val_mse: 0.1179 - val_mae: 0.3236 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 294/500

Epoch 00294: val_loss improved from 0.11768 to 0.11724, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0562 - val_loss: 0.1172 - val_mse: 0.1172 - val_mae: 0.3227 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 295/500

Epoch 00295: val_loss did not improve from 0.11724
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0559 - val_loss: 0.1174 - val_mse: 0.1174 - val_mae: 0.3229 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 296/500

Epoch 00296: val_loss did not improve from 0.11724
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0555 - val_loss: 0.1173 - val_mse: 0.1173 - val_mae: 0.3229 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 297/500

Epoch 00297: val_loss did not improve from 0.11724
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0562 - val_loss: 0.1173 - val_mse: 0.1173 - val_mae: 0.3228 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 298/500

Epoch 00298: val_loss improved from 0.11724 to 0.11713, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0555 - val_loss: 0.1171 - val_mse: 0.1171 - val_mae: 0.3226 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 299/500

Epoch 00299: val_loss improved from 0.11713 to 0.11709, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0584 - val_loss: 0.1171 - val_mse: 0.1171 - val_mae: 0.3225 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 300/500

Epoch 00300: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0575 - val_loss: 0.1172 - val_mse: 0.1172 - val_mae: 0.3227 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 301/500

Epoch 00301: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.1172 - val_mse: 0.1172 - val_mae: 0.3227 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 302/500

Epoch 00302: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0560 - val_loss: 0.1174 - val_mse: 0.1174 - val_mae: 0.3230 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 303/500

Epoch 00303: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0578 - val_loss: 0.1176 - val_mse: 0.1176 - val_mae: 0.3233 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 304/500

Epoch 00304: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0563 - val_loss: 0.1180 - val_mse: 0.1180 - val_mae: 0.3239 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 305/500

Epoch 00305: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0556 - val_loss: 0.1184 - val_mse: 0.1184 - val_mae: 0.3244 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 306/500

Epoch 00306: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0563 - val_loss: 0.1184 - val_mse: 0.1184 - val_mae: 0.3244 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 307/500

Epoch 00307: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0579 - val_loss: 0.1182 - val_mse: 0.1182 - val_mae: 0.3242 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 308/500

Epoch 00308: val_loss did not improve from 0.11709
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0588 - val_loss: 0.1173 - val_mse: 0.1173 - val_mae: 0.3229 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 309/500

Epoch 00309: val_loss improved from 0.11709 to 0.11635, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0581 - val_loss: 0.1164 - val_mse: 0.1164 - val_mae: 0.3215 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 310/500

Epoch 00310: val_loss improved from 0.11635 to 0.11572, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0547 - val_loss: 0.1157 - val_mse: 0.1157 - val_mae: 0.3205 - lr: 1.0000e-05 - 85ms/epoch - 9ms/step
Epoch 311/500

Epoch 00311: val_loss improved from 0.11572 to 0.11539, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0554 - val_loss: 0.1154 - val_mse: 0.1154 - val_mae: 0.3201 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 312/500

Epoch 00312: val_loss improved from 0.11539 to 0.11520, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0555 - val_loss: 0.1152 - val_mse: 0.1152 - val_mae: 0.3198 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 313/500

Epoch 00313: val_loss improved from 0.11520 to 0.11490, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0596 - val_loss: 0.1149 - val_mse: 0.1149 - val_mae: 0.3193 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 314/500

Epoch 00314: val_loss improved from 0.11490 to 0.11480, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0539 - val_loss: 0.1148 - val_mse: 0.1148 - val_mae: 0.3192 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 315/500

Epoch 00315: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.1149 - val_mse: 0.1149 - val_mae: 0.3194 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 316/500

Epoch 00316: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0560 - val_loss: 0.1153 - val_mse: 0.1153 - val_mae: 0.3198 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 317/500

Epoch 00317: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.1156 - val_mse: 0.1156 - val_mae: 0.3203 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 318/500

Epoch 00318: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0551 - val_loss: 0.1159 - val_mse: 0.1159 - val_mae: 0.3207 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 319/500

Epoch 00319: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0566 - val_loss: 0.1160 - val_mse: 0.1160 - val_mae: 0.3209 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 320/500

Epoch 00320: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0555 - val_loss: 0.1156 - val_mse: 0.1156 - val_mae: 0.3203 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 321/500

Epoch 00321: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0556 - val_loss: 0.1154 - val_mse: 0.1154 - val_mae: 0.3201 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 322/500

Epoch 00322: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0556 - val_loss: 0.1154 - val_mse: 0.1154 - val_mae: 0.3200 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 323/500

Epoch 00323: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0539 - val_loss: 0.1155 - val_mse: 0.1155 - val_mae: 0.3202 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 324/500

Epoch 00324: val_loss did not improve from 0.11480
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0552 - val_loss: 0.1151 - val_mse: 0.1151 - val_mae: 0.3197 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 325/500

Epoch 00325: val_loss improved from 0.11480 to 0.11477, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.1148 - val_mse: 0.1148 - val_mae: 0.3191 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 326/500

Epoch 00326: val_loss improved from 0.11477 to 0.11473, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.1147 - val_mse: 0.1147 - val_mae: 0.3191 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 327/500

Epoch 00327: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0544 - val_loss: 0.1148 - val_mse: 0.1148 - val_mae: 0.3191 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 328/500

Epoch 00328: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0545 - val_loss: 0.1150 - val_mse: 0.1150 - val_mae: 0.3195 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 329/500

Epoch 00329: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0571 - val_loss: 0.1150 - val_mse: 0.1150 - val_mae: 0.3194 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 330/500

Epoch 00330: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0564 - val_loss: 0.1151 - val_mse: 0.1151 - val_mae: 0.3196 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 331/500

Epoch 00331: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0551 - val_loss: 0.1151 - val_mse: 0.1151 - val_mae: 0.3196 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 332/500

Epoch 00332: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0560 - val_loss: 0.1150 - val_mse: 0.1150 - val_mae: 0.3195 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 333/500

Epoch 00333: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0556 - val_loss: 0.1149 - val_mse: 0.1149 - val_mae: 0.3195 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 334/500

Epoch 00334: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0521 - val_loss: 0.1150 - val_mse: 0.1150 - val_mae: 0.3195 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 335/500

Epoch 00335: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0546 - val_loss: 0.1154 - val_mse: 0.1154 - val_mae: 0.3202 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 336/500

Epoch 00336: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0546 - val_loss: 0.1157 - val_mse: 0.1157 - val_mae: 0.3205 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 337/500

Epoch 00337: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.1155 - val_mse: 0.1155 - val_mae: 0.3203 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 338/500

Epoch 00338: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0533 - val_loss: 0.1157 - val_mse: 0.1157 - val_mae: 0.3206 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 339/500

Epoch 00339: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0538 - val_loss: 0.1159 - val_mse: 0.1159 - val_mae: 0.3208 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 340/500

Epoch 00340: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.1158 - val_mse: 0.1158 - val_mae: 0.3208 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 341/500

Epoch 00341: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0550 - val_loss: 0.1158 - val_mse: 0.1158 - val_mae: 0.3208 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 342/500

Epoch 00342: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0538 - val_loss: 0.1160 - val_mse: 0.1160 - val_mae: 0.3211 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 343/500

Epoch 00343: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0537 - val_loss: 0.1160 - val_mse: 0.1160 - val_mae: 0.3210 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 344/500

Epoch 00344: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0579 - val_loss: 0.1157 - val_mse: 0.1157 - val_mae: 0.3205 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 345/500

Epoch 00345: val_loss did not improve from 0.11473
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0554 - val_loss: 0.1151 - val_mse: 0.1151 - val_mae: 0.3198 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 346/500

Epoch 00346: val_loss improved from 0.11473 to 0.11468, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0565 - val_loss: 0.1147 - val_mse: 0.1147 - val_mae: 0.3191 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 347/500

Epoch 00347: val_loss improved from 0.11468 to 0.11448, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0543 - val_loss: 0.1145 - val_mse: 0.1145 - val_mae: 0.3188 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 348/500

Epoch 00348: val_loss improved from 0.11448 to 0.11417, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0572 - val_loss: 0.1142 - val_mse: 0.1142 - val_mae: 0.3184 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 349/500

Epoch 00349: val_loss improved from 0.11417 to 0.11403, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0580 - val_loss: 0.1140 - val_mse: 0.1140 - val_mae: 0.3182 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 350/500

Epoch 00350: val_loss improved from 0.11403 to 0.11397, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0556 - val_loss: 0.1140 - val_mse: 0.1140 - val_mae: 0.3181 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 351/500

Epoch 00351: val_loss improved from 0.11397 to 0.11370, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0565 - val_loss: 0.1137 - val_mse: 0.1137 - val_mae: 0.3177 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 352/500

Epoch 00352: val_loss improved from 0.11370 to 0.11353, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0531 - val_loss: 0.1135 - val_mse: 0.1135 - val_mae: 0.3174 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 353/500

Epoch 00353: val_loss improved from 0.11353 to 0.11325, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0552 - val_loss: 0.1133 - val_mse: 0.1133 - val_mae: 0.3170 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 354/500

Epoch 00354: val_loss improved from 0.11325 to 0.11309, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.1131 - val_mse: 0.1131 - val_mae: 0.3167 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 355/500

Epoch 00355: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0538 - val_loss: 0.1133 - val_mse: 0.1133 - val_mae: 0.3171 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 356/500

Epoch 00356: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0538 - val_loss: 0.1133 - val_mse: 0.1133 - val_mae: 0.3171 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 357/500

Epoch 00357: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0536 - val_loss: 0.1135 - val_mse: 0.1135 - val_mae: 0.3173 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 358/500

Epoch 00358: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0559 - val_loss: 0.1134 - val_mse: 0.1134 - val_mae: 0.3173 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 359/500

Epoch 00359: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0534 - val_loss: 0.1133 - val_mse: 0.1133 - val_mae: 0.3171 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 360/500

Epoch 00360: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0538 - val_loss: 0.1133 - val_mse: 0.1133 - val_mae: 0.3170 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 361/500

Epoch 00361: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0565 - val_loss: 0.1134 - val_mse: 0.1134 - val_mae: 0.3172 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 362/500

Epoch 00362: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0548 - val_loss: 0.1134 - val_mse: 0.1134 - val_mae: 0.3172 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 363/500

Epoch 00363: val_loss did not improve from 0.11309
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0541 - val_loss: 0.1133 - val_mse: 0.1133 - val_mae: 0.3171 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 364/500

Epoch 00364: val_loss improved from 0.11309 to 0.11304, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0546 - val_loss: 0.1130 - val_mse: 0.1130 - val_mae: 0.3167 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 365/500

Epoch 00365: val_loss improved from 0.11304 to 0.11297, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0521 - val_loss: 0.1130 - val_mse: 0.1130 - val_mae: 0.3166 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 366/500

Epoch 00366: val_loss did not improve from 0.11297
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0528 - val_loss: 0.1131 - val_mse: 0.1131 - val_mae: 0.3168 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 367/500

Epoch 00367: val_loss improved from 0.11297 to 0.11296, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0563 - val_loss: 0.1130 - val_mse: 0.1130 - val_mae: 0.3166 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 368/500

Epoch 00368: val_loss improved from 0.11296 to 0.11281, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0550 - val_loss: 0.1128 - val_mse: 0.1128 - val_mae: 0.3163 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 369/500

Epoch 00369: val_loss improved from 0.11281 to 0.11238, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0560 - val_loss: 0.1124 - val_mse: 0.1124 - val_mae: 0.3157 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 370/500

Epoch 00370: val_loss did not improve from 0.11238
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0559 - val_loss: 0.1124 - val_mse: 0.1124 - val_mae: 0.3157 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 371/500

Epoch 00371: val_loss improved from 0.11238 to 0.11229, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0551 - val_loss: 0.1123 - val_mse: 0.1123 - val_mae: 0.3155 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 372/500

Epoch 00372: val_loss did not improve from 0.11229
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0565 - val_loss: 0.1124 - val_mse: 0.1124 - val_mae: 0.3157 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 373/500

Epoch 00373: val_loss did not improve from 0.11229
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0530 - val_loss: 0.1125 - val_mse: 0.1125 - val_mae: 0.3159 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 374/500

Epoch 00374: val_loss improved from 0.11229 to 0.11211, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0537 - val_loss: 0.1121 - val_mse: 0.1121 - val_mae: 0.3153 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 375/500

Epoch 00375: val_loss improved from 0.11211 to 0.11191, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0574 - val_loss: 0.1119 - val_mse: 0.1119 - val_mae: 0.3150 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 376/500

Epoch 00376: val_loss improved from 0.11191 to 0.11172, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0544 - val_loss: 0.1117 - val_mse: 0.1117 - val_mae: 0.3147 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 377/500

Epoch 00377: val_loss improved from 0.11172 to 0.11165, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0521 - val_loss: 0.1116 - val_mse: 0.1116 - val_mae: 0.3146 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 378/500

Epoch 00378: val_loss did not improve from 0.11165
10/10 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0598 - val_loss: 0.1118 - val_mse: 0.1118 - val_mae: 0.3148 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 379/500

Epoch 00379: val_loss did not improve from 0.11165
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0528 - val_loss: 0.1119 - val_mse: 0.1119 - val_mae: 0.3150 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 380/500

Epoch 00380: val_loss did not improve from 0.11165
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0554 - val_loss: 0.1119 - val_mse: 0.1119 - val_mae: 0.3150 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 381/500

Epoch 00381: val_loss did not improve from 0.11165
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0526 - val_loss: 0.1123 - val_mse: 0.1123 - val_mae: 0.3157 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 382/500

Epoch 00382: val_loss did not improve from 0.11165
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0555 - val_loss: 0.1125 - val_mse: 0.1125 - val_mae: 0.3159 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 383/500

Epoch 00383: val_loss did not improve from 0.11165
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0556 - val_loss: 0.1122 - val_mse: 0.1122 - val_mae: 0.3155 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 384/500

Epoch 00384: val_loss did not improve from 0.11165
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0558 - val_loss: 0.1116 - val_mse: 0.1116 - val_mae: 0.3146 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 385/500

Epoch 00385: val_loss improved from 0.11165 to 0.11138, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0544 - val_loss: 0.1114 - val_mse: 0.1114 - val_mae: 0.3143 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 386/500

Epoch 00386: val_loss improved from 0.11138 to 0.11095, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0540 - val_loss: 0.1109 - val_mse: 0.1109 - val_mae: 0.3136 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 387/500

Epoch 00387: val_loss did not improve from 0.11095
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0546 - val_loss: 0.1110 - val_mse: 0.1110 - val_mae: 0.3136 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 388/500

Epoch 00388: val_loss improved from 0.11095 to 0.11090, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0579 - val_loss: 0.1109 - val_mse: 0.1109 - val_mae: 0.3135 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 389/500

Epoch 00389: val_loss improved from 0.11090 to 0.11061, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0545 - val_loss: 0.1106 - val_mse: 0.1106 - val_mae: 0.3131 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 390/500

Epoch 00390: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0551 - val_loss: 0.1106 - val_mse: 0.1106 - val_mae: 0.3131 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 391/500

Epoch 00391: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0543 - val_loss: 0.1109 - val_mse: 0.1109 - val_mae: 0.3135 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 392/500

Epoch 00392: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0556 - val_loss: 0.1108 - val_mse: 0.1108 - val_mae: 0.3134 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 393/500

Epoch 00393: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0566 - val_loss: 0.1108 - val_mse: 0.1108 - val_mae: 0.3134 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 394/500

Epoch 00394: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.1111 - val_mse: 0.1111 - val_mae: 0.3139 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 395/500

Epoch 00395: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0541 - val_loss: 0.1112 - val_mse: 0.1112 - val_mae: 0.3141 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 396/500

Epoch 00396: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0556 - val_loss: 0.1115 - val_mse: 0.1115 - val_mae: 0.3144 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 397/500

Epoch 00397: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0539 - val_loss: 0.1116 - val_mse: 0.1116 - val_mae: 0.3146 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 398/500

Epoch 00398: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0542 - val_loss: 0.1116 - val_mse: 0.1116 - val_mae: 0.3146 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 399/500

Epoch 00399: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0562 - val_loss: 0.1113 - val_mse: 0.1113 - val_mae: 0.3141 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 400/500

Epoch 00400: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.1112 - val_mse: 0.1112 - val_mae: 0.3140 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 401/500

Epoch 00401: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0543 - val_loss: 0.1109 - val_mse: 0.1109 - val_mae: 0.3135 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 402/500

Epoch 00402: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0526 - val_loss: 0.1108 - val_mse: 0.1108 - val_mae: 0.3134 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 403/500

Epoch 00403: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0516 - val_loss: 0.1108 - val_mse: 0.1108 - val_mae: 0.3134 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 404/500

Epoch 00404: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0564 - val_loss: 0.1111 - val_mse: 0.1111 - val_mae: 0.3138 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 405/500

Epoch 00405: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0557 - val_loss: 0.1116 - val_mse: 0.1116 - val_mae: 0.3146 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 406/500

Epoch 00406: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0566 - val_loss: 0.1120 - val_mse: 0.1120 - val_mae: 0.3152 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 407/500

Epoch 00407: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0543 - val_loss: 0.1117 - val_mse: 0.1117 - val_mae: 0.3147 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 408/500

Epoch 00408: val_loss did not improve from 0.11061
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0544 - val_loss: 0.1111 - val_mse: 0.1111 - val_mae: 0.3139 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 409/500

Epoch 00409: val_loss improved from 0.11061 to 0.11055, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0526 - val_loss: 0.1105 - val_mse: 0.1105 - val_mae: 0.3130 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 410/500

Epoch 00410: val_loss improved from 0.11055 to 0.11054, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0559 - val_loss: 0.1105 - val_mse: 0.1105 - val_mae: 0.3130 - lr: 1.0000e-05 - 75ms/epoch - 8ms/step
Epoch 411/500

Epoch 00411: val_loss did not improve from 0.11054
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0542 - val_loss: 0.1107 - val_mse: 0.1107 - val_mae: 0.3133 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 412/500

Epoch 00412: val_loss did not improve from 0.11054
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0542 - val_loss: 0.1108 - val_mse: 0.1108 - val_mae: 0.3134 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 413/500

Epoch 00413: val_loss improved from 0.11054 to 0.11041, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.1104 - val_mse: 0.1104 - val_mae: 0.3128 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 414/500

Epoch 00414: val_loss improved from 0.11041 to 0.11008, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0547 - val_loss: 0.1101 - val_mse: 0.1101 - val_mae: 0.3123 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 415/500

Epoch 00415: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0535 - val_loss: 0.1104 - val_mse: 0.1104 - val_mae: 0.3128 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 416/500

Epoch 00416: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0520 - val_loss: 0.1107 - val_mse: 0.1107 - val_mae: 0.3132 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 417/500

Epoch 00417: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0541 - val_loss: 0.1111 - val_mse: 0.1111 - val_mae: 0.3138 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 418/500

Epoch 00418: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0532 - val_loss: 0.1110 - val_mse: 0.1110 - val_mae: 0.3137 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 419/500

Epoch 00419: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0538 - val_loss: 0.1109 - val_mse: 0.1109 - val_mae: 0.3135 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 420/500

Epoch 00420: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.1110 - val_mse: 0.1110 - val_mae: 0.3138 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 421/500

Epoch 00421: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0532 - val_loss: 0.1113 - val_mse: 0.1113 - val_mae: 0.3142 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 422/500

Epoch 00422: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0539 - val_loss: 0.1119 - val_mse: 0.1119 - val_mae: 0.3150 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 423/500

Epoch 00423: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0512 - val_loss: 0.1124 - val_mse: 0.1124 - val_mae: 0.3158 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 424/500

Epoch 00424: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0539 - val_loss: 0.1126 - val_mse: 0.1126 - val_mae: 0.3160 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 425/500

Epoch 00425: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0541 - val_loss: 0.1127 - val_mse: 0.1127 - val_mae: 0.3163 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 426/500

Epoch 00426: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0537 - val_loss: 0.1126 - val_mse: 0.1126 - val_mae: 0.3160 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 427/500

Epoch 00427: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0557 - val_loss: 0.1124 - val_mse: 0.1124 - val_mae: 0.3159 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 428/500

Epoch 00428: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0535 - val_loss: 0.1129 - val_mse: 0.1129 - val_mae: 0.3166 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 429/500

Epoch 00429: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0554 - val_loss: 0.1125 - val_mse: 0.1125 - val_mae: 0.3160 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 430/500

Epoch 00430: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0546 - val_loss: 0.1117 - val_mse: 0.1117 - val_mae: 0.3148 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 431/500

Epoch 00431: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0561 - val_loss: 0.1111 - val_mse: 0.1111 - val_mae: 0.3139 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 432/500

Epoch 00432: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0539 - val_loss: 0.1109 - val_mse: 0.1109 - val_mae: 0.3136 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 433/500

Epoch 00433: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0538 - val_loss: 0.1105 - val_mse: 0.1105 - val_mae: 0.3129 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 434/500

Epoch 00434: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0563 - val_loss: 0.1105 - val_mse: 0.1105 - val_mae: 0.3130 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 435/500

Epoch 00435: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.1112 - val_mse: 0.1112 - val_mae: 0.3140 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 436/500

Epoch 00436: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0569 - val_loss: 0.1114 - val_mse: 0.1114 - val_mae: 0.3144 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 437/500

Epoch 00437: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0552 - val_loss: 0.1112 - val_mse: 0.1112 - val_mae: 0.3141 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 438/500

Epoch 00438: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.1113 - val_mse: 0.1113 - val_mae: 0.3142 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 439/500

Epoch 00439: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0537 - val_loss: 0.1118 - val_mse: 0.1118 - val_mae: 0.3150 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 440/500

Epoch 00440: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0545 - val_loss: 0.1120 - val_mse: 0.1120 - val_mae: 0.3153 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 441/500

Epoch 00441: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0539 - val_loss: 0.1118 - val_mse: 0.1118 - val_mae: 0.3150 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 442/500

Epoch 00442: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0526 - val_loss: 0.1113 - val_mse: 0.1113 - val_mae: 0.3143 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 443/500

Epoch 00443: val_loss did not improve from 0.11008
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0554 - val_loss: 0.1106 - val_mse: 0.1106 - val_mae: 0.3132 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 444/500

Epoch 00444: val_loss improved from 0.11008 to 0.10981, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0561 - val_loss: 0.1098 - val_mse: 0.1098 - val_mae: 0.3120 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 445/500

Epoch 00445: val_loss improved from 0.10981 to 0.10936, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0522 - val_loss: 0.1094 - val_mse: 0.1094 - val_mae: 0.3113 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 446/500

Epoch 00446: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.1094 - val_mse: 0.1094 - val_mae: 0.3114 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 447/500

Epoch 00447: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0557 - val_loss: 0.1101 - val_mse: 0.1101 - val_mae: 0.3124 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 448/500

Epoch 00448: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0555 - val_loss: 0.1106 - val_mse: 0.1106 - val_mae: 0.3132 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 449/500

Epoch 00449: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0549 - val_loss: 0.1105 - val_mse: 0.1105 - val_mae: 0.3131 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 450/500

Epoch 00450: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0538 - val_loss: 0.1103 - val_mse: 0.1103 - val_mae: 0.3127 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 451/500

Epoch 00451: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0538 - val_loss: 0.1098 - val_mse: 0.1098 - val_mae: 0.3119 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 452/500

Epoch 00452: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0522 - val_loss: 0.1097 - val_mse: 0.1097 - val_mae: 0.3118 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 453/500

Epoch 00453: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0547 - val_loss: 0.1097 - val_mse: 0.1097 - val_mae: 0.3119 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 454/500

Epoch 00454: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0542 - val_loss: 0.1099 - val_mse: 0.1099 - val_mae: 0.3122 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 455/500

Epoch 00455: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0524 - val_loss: 0.1100 - val_mse: 0.1100 - val_mae: 0.3123 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 456/500

Epoch 00456: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0552 - val_loss: 0.1098 - val_mse: 0.1098 - val_mae: 0.3121 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 457/500

Epoch 00457: val_loss did not improve from 0.10936
10/10 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0521 - val_loss: 0.1095 - val_mse: 0.1095 - val_mae: 0.3116 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 458/500

Epoch 00458: val_loss improved from 0.10936 to 0.10890, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0547 - val_loss: 0.1089 - val_mse: 0.1089 - val_mae: 0.3107 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 459/500

Epoch 00459: val_loss improved from 0.10890 to 0.10854, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0574 - val_loss: 0.1085 - val_mse: 0.1085 - val_mae: 0.3101 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 460/500

Epoch 00460: val_loss improved from 0.10854 to 0.10826, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0546 - val_loss: 0.1083 - val_mse: 0.1083 - val_mae: 0.3097 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 461/500

Epoch 00461: val_loss improved from 0.10826 to 0.10807, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0532 - val_loss: 0.1081 - val_mse: 0.1081 - val_mae: 0.3094 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 462/500

Epoch 00462: val_loss improved from 0.10807 to 0.10740, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0538 - val_loss: 0.1074 - val_mse: 0.1074 - val_mae: 0.3084 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 463/500

Epoch 00463: val_loss improved from 0.10740 to 0.10729, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.1073 - val_mse: 0.1073 - val_mae: 0.3082 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 464/500

Epoch 00464: val_loss did not improve from 0.10729
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.1075 - val_mse: 0.1075 - val_mae: 0.3084 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 465/500

Epoch 00465: val_loss did not improve from 0.10729
10/10 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0561 - val_loss: 0.1074 - val_mse: 0.1074 - val_mae: 0.3084 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 466/500

Epoch 00466: val_loss did not improve from 0.10729
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0552 - val_loss: 0.1075 - val_mse: 0.1075 - val_mae: 0.3085 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 467/500

Epoch 00467: val_loss did not improve from 0.10729
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0545 - val_loss: 0.1076 - val_mse: 0.1076 - val_mae: 0.3087 - lr: 1.0000e-05 - 51ms/epoch - 5ms/step
Epoch 468/500

Epoch 00468: val_loss did not improve from 0.10729
10/10 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0552 - val_loss: 0.1073 - val_mse: 0.1073 - val_mae: 0.3082 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 469/500

Epoch 00469: val_loss did not improve from 0.10729
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0533 - val_loss: 0.1073 - val_mse: 0.1073 - val_mae: 0.3082 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 470/500

Epoch 00470: val_loss improved from 0.10729 to 0.10671, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0541 - val_loss: 0.1067 - val_mse: 0.1067 - val_mae: 0.3073 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 471/500

Epoch 00471: val_loss improved from 0.10671 to 0.10646, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0544 - val_loss: 0.1065 - val_mse: 0.1065 - val_mae: 0.3069 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 472/500

Epoch 00472: val_loss improved from 0.10646 to 0.10628, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0562 - val_loss: 0.1063 - val_mse: 0.1063 - val_mae: 0.3066 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 473/500

Epoch 00473: val_loss improved from 0.10628 to 0.10609, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0557 - val_loss: 0.1061 - val_mse: 0.1061 - val_mae: 0.3064 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 474/500

Epoch 00474: val_loss did not improve from 0.10609
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0525 - val_loss: 0.1067 - val_mse: 0.1067 - val_mae: 0.3073 - lr: 1.0000e-05 - 55ms/epoch - 6ms/step
Epoch 475/500

Epoch 00475: val_loss did not improve from 0.10609
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0523 - val_loss: 0.1068 - val_mse: 0.1068 - val_mae: 0.3075 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 476/500

Epoch 00476: val_loss did not improve from 0.10609
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0541 - val_loss: 0.1068 - val_mse: 0.1068 - val_mae: 0.3074 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 477/500

Epoch 00477: val_loss did not improve from 0.10609
10/10 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0523 - val_loss: 0.1067 - val_mse: 0.1067 - val_mae: 0.3073 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 478/500

Epoch 00478: val_loss did not improve from 0.10609
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0519 - val_loss: 0.1067 - val_mse: 0.1067 - val_mae: 0.3073 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 479/500

Epoch 00479: val_loss did not improve from 0.10609
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0514 - val_loss: 0.1066 - val_mse: 0.1066 - val_mae: 0.3071 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 480/500

Epoch 00480: val_loss did not improve from 0.10609
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0558 - val_loss: 0.1066 - val_mse: 0.1066 - val_mae: 0.3072 - lr: 1.0000e-05 - 55ms/epoch - 5ms/step
Epoch 481/500

Epoch 00481: val_loss did not improve from 0.10609
10/10 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0504 - val_loss: 0.1067 - val_mse: 0.1067 - val_mae: 0.3073 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 482/500

Epoch 00482: val_loss improved from 0.10609 to 0.10605, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0547 - val_loss: 0.1061 - val_mse: 0.1061 - val_mae: 0.3063 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 483/500

Epoch 00483: val_loss improved from 0.10605 to 0.10552, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0536 - val_loss: 0.1055 - val_mse: 0.1055 - val_mae: 0.3055 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 484/500

Epoch 00484: val_loss improved from 0.10552 to 0.10517, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0514 - val_loss: 0.1052 - val_mse: 0.1052 - val_mae: 0.3050 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 485/500

Epoch 00485: val_loss did not improve from 0.10517
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0534 - val_loss: 0.1054 - val_mse: 0.1054 - val_mae: 0.3054 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 486/500

Epoch 00486: val_loss did not improve from 0.10517
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0551 - val_loss: 0.1056 - val_mse: 0.1056 - val_mae: 0.3057 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 487/500

Epoch 00487: val_loss did not improve from 0.10517
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0520 - val_loss: 0.1060 - val_mse: 0.1060 - val_mae: 0.3063 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 488/500

Epoch 00488: val_loss did not improve from 0.10517
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0540 - val_loss: 0.1058 - val_mse: 0.1058 - val_mae: 0.3060 - lr: 1.0000e-05 - 54ms/epoch - 5ms/step
Epoch 489/500

Epoch 00489: val_loss did not improve from 0.10517
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0537 - val_loss: 0.1053 - val_mse: 0.1053 - val_mae: 0.3052 - lr: 1.0000e-05 - 52ms/epoch - 5ms/step
Epoch 490/500

Epoch 00490: val_loss did not improve from 0.10517
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0532 - val_loss: 0.1052 - val_mse: 0.1052 - val_mae: 0.3050 - lr: 1.0000e-05 - 53ms/epoch - 5ms/step
Epoch 491/500

Epoch 00491: val_loss improved from 0.10517 to 0.10512, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0516 - val_loss: 0.1051 - val_mse: 0.1051 - val_mae: 0.3049 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 492/500

Epoch 00492: val_loss did not improve from 0.10512
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0545 - val_loss: 0.1052 - val_mse: 0.1052 - val_mae: 0.3049 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 493/500

Epoch 00493: val_loss improved from 0.10512 to 0.10483, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0524 - val_loss: 0.1048 - val_mse: 0.1048 - val_mae: 0.3044 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 494/500

Epoch 00494: val_loss improved from 0.10483 to 0.10409, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0535 - val_loss: 0.1041 - val_mse: 0.1041 - val_mae: 0.3033 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 495/500

Epoch 00495: val_loss improved from 0.10409 to 0.10342, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0530 - val_loss: 0.1034 - val_mse: 0.1034 - val_mae: 0.3022 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 496/500

Epoch 00496: val_loss improved from 0.10342 to 0.10309, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0550 - val_loss: 0.1031 - val_mse: 0.1031 - val_mae: 0.3017 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 497/500

Epoch 00497: val_loss improved from 0.10309 to 0.10282, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0531 - val_loss: 0.1028 - val_mse: 0.1028 - val_mae: 0.3013 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 498/500

Epoch 00498: val_loss improved from 0.10282 to 0.10252, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0548 - val_loss: 0.1025 - val_mse: 0.1025 - val_mae: 0.3008 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 499/500

Epoch 00499: val_loss improved from 0.10252 to 0.10212, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0517 - val_loss: 0.1021 - val_mse: 0.1021 - val_mae: 0.3002 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 500/500

Epoch 00500: val_loss improved from 0.10212 to 0.10209, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0545 - val_loss: 0.1021 - val_mse: 0.1021 - val_mae: 0.3002 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step

SMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 23.38002191723926 
RMSE:	 4.835289227878645 
MAPE:	 3.8675720673818827

EMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 35.056668726825066 
RMSE:	 5.920867227596399 
MAPE:	 4.704877912816018

WMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 44.87192646385527 
RMSE:	 6.698651092858566 
MAPE:	 5.33068935026581

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 53.079656203261706 
RMSE:	 7.285578645739933 
MAPE:	 5.726487515550782
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17059.325, Time=4.32 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.28 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16133.019, Time=5.90 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=5.66 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16091.980, Time=7.54 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16009.844, Time=12.16 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-15757.180, Time=8.36 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17029.439, Time=4.44 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17000.917, Time=3.16 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=45.027, Time=4.20 sec

Best model:  ARIMA(1,3,1)(0,0,0)[0]          
Total fit time: 60.041 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 1)   Log Likelihood                8554.662
Date:                Sun, 12 Dec 2021   AIC                         -17059.325
Time:                        19:21:45   BIC                         -16942.054
Sample:                             0   HQIC                        -17014.288
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -1.409e-10   5.52e-21  -2.55e+10      0.000   -1.41e-10   -1.41e-10
x2         -1.378e-10   5.47e-21  -2.52e+10      0.000   -1.38e-10   -1.38e-10
x3         -1.323e-10   5.35e-21  -2.47e+10      0.000   -1.32e-10   -1.32e-10
x4             1.0000   5.41e-21   1.85e+20      0.000       1.000       1.000
x5         -1.221e-10   5.15e-21  -2.37e+10      0.000   -1.22e-10   -1.22e-10
x6         -8.465e-10    1.3e-20  -6.53e+10      0.000   -8.47e-10   -8.47e-10
x7           -1.3e-10   5.32e-21  -2.44e+10      0.000    -1.3e-10    -1.3e-10
x8         -1.267e-10   5.27e-21  -2.41e+10      0.000   -1.27e-10   -1.27e-10
x9         -2.032e-11   6.67e-22  -3.05e+10      0.000   -2.03e-11   -2.03e-11
x10        -5.319e-11    2.3e-21  -2.31e+10      0.000   -5.32e-11   -5.32e-11
x11        -1.275e-10   5.28e-21  -2.42e+10      0.000   -1.28e-10   -1.28e-10
x12        -1.262e-10   5.23e-21  -2.41e+10      0.000   -1.26e-10   -1.26e-10
x13        -1.339e-10   5.39e-21  -2.49e+10      0.000   -1.34e-10   -1.34e-10
x14        -1.092e-09   1.55e-20  -7.06e+10      0.000   -1.09e-09   -1.09e-09
x15        -1.342e-10   5.42e-21  -2.48e+10      0.000   -1.34e-10   -1.34e-10
x16         -2.01e-10   6.63e-21  -3.03e+10      0.000   -2.01e-10   -2.01e-10
x17        -1.144e-10   5.01e-21  -2.29e+10      0.000   -1.14e-10   -1.14e-10
x18        -9.245e-11   4.49e-21  -2.06e+10      0.000   -9.24e-11   -9.24e-11
x19        -1.646e-10   6.01e-21  -2.74e+10      0.000   -1.65e-10   -1.65e-10
x20        -2.482e-10   7.35e-21  -3.37e+10      0.000   -2.48e-10   -2.48e-10
x21        -3.385e-12   3.14e-24  -1.08e+12      0.000   -3.39e-12   -3.39e-12
x22        -8.066e-11   2.47e-23  -3.26e+12      0.000   -8.07e-11   -8.07e-11
ar.L1         -0.2877   2.48e-22  -1.16e+21      0.000      -0.288      -0.288
ma.L1         -0.9134   1.05e-21   -8.7e+20      0.000      -0.913      -0.913
sigma2      9.332e-11   6.96e-11      1.340      0.180   -4.32e-11     2.3e-10
===================================================================================
Ljung-Box (L1) (Q):                  84.37   Jarque-Bera (JB):           4308764.36
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             5.22
Prob(H) (two-sided):                  0.00   Kurtosis:                       361.26
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.32e+42. Standard errors may be unstable.
ARIMA order: (1, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.94953, saving model to LSTM7.h5
45/45 - 3s - loss: 0.3493 - mse: 0.3493 - mae: 0.4597 - val_loss: 0.9495 - val_mse: 0.9495 - val_mae: 0.9524 - lr: 0.0010 - 3s/epoch - 58ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.94953 to 0.62787, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0451 - mse: 0.0451 - mae: 0.1715 - val_loss: 0.6279 - val_mse: 0.6279 - val_mae: 0.7695 - lr: 0.0010 - 189ms/epoch - 4ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.62787 to 0.46000, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0266 - mse: 0.0266 - mae: 0.1299 - val_loss: 0.4600 - val_mse: 0.4600 - val_mae: 0.6537 - lr: 0.0010 - 185ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.46000 to 0.37808, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0187 - mse: 0.0187 - mae: 0.1073 - val_loss: 0.3781 - val_mse: 0.3781 - val_mae: 0.5890 - lr: 0.0010 - 188ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.37808 to 0.35518, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0156 - mse: 0.0156 - mae: 0.1004 - val_loss: 0.3552 - val_mse: 0.3552 - val_mae: 0.5700 - lr: 0.0010 - 183ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.35518 to 0.33869, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0142 - mse: 0.0142 - mae: 0.0935 - val_loss: 0.3387 - val_mse: 0.3387 - val_mae: 0.5562 - lr: 0.0010 - 181ms/epoch - 4ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.33869 to 0.32261, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0136 - mse: 0.0136 - mae: 0.0907 - val_loss: 0.3226 - val_mse: 0.3226 - val_mae: 0.5424 - lr: 0.0010 - 175ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.32261
45/45 - 0s - loss: 0.0133 - mse: 0.0133 - mae: 0.0919 - val_loss: 0.3284 - val_mse: 0.3284 - val_mae: 0.5479 - lr: 0.0010 - 162ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.32261 to 0.29843, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0848 - val_loss: 0.2984 - val_mse: 0.2984 - val_mae: 0.5212 - lr: 0.0010 - 181ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.29843 to 0.27395, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0117 - mse: 0.0117 - mae: 0.0854 - val_loss: 0.2740 - val_mse: 0.2740 - val_mae: 0.4989 - lr: 0.0010 - 174ms/epoch - 4ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.27395 to 0.26507, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0100 - mse: 0.0100 - mae: 0.0796 - val_loss: 0.2651 - val_mse: 0.2651 - val_mae: 0.4904 - lr: 0.0010 - 190ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.26507 to 0.26086, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0106 - mse: 0.0106 - mae: 0.0821 - val_loss: 0.2609 - val_mse: 0.2609 - val_mae: 0.4867 - lr: 0.0010 - 200ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.26086
45/45 - 0s - loss: 0.0109 - mse: 0.0109 - mae: 0.0820 - val_loss: 0.2672 - val_mse: 0.2672 - val_mae: 0.4934 - lr: 0.0010 - 175ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.26086 to 0.25533, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0824 - val_loss: 0.2553 - val_mse: 0.2553 - val_mae: 0.4820 - lr: 0.0010 - 187ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.25533
45/45 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0831 - val_loss: 0.2588 - val_mse: 0.2588 - val_mae: 0.4857 - lr: 0.0010 - 167ms/epoch - 4ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.25533 to 0.23311, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0117 - mse: 0.0117 - mae: 0.0848 - val_loss: 0.2331 - val_mse: 0.2331 - val_mae: 0.4599 - lr: 0.0010 - 185ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.23311 to 0.20135, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0806 - val_loss: 0.2014 - val_mse: 0.2014 - val_mae: 0.4262 - lr: 0.0010 - 201ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.20135
45/45 - 0s - loss: 0.0100 - mse: 0.0100 - mae: 0.0786 - val_loss: 0.2293 - val_mse: 0.2293 - val_mae: 0.4568 - lr: 0.0010 - 170ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.20135
45/45 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0843 - val_loss: 0.2187 - val_mse: 0.2187 - val_mae: 0.4459 - lr: 0.0010 - 172ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.20135 to 0.19748, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0101 - mse: 0.0101 - mae: 0.0784 - val_loss: 0.1975 - val_mse: 0.1975 - val_mae: 0.4228 - lr: 0.0010 - 176ms/epoch - 4ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.19748
45/45 - 0s - loss: 0.0103 - mse: 0.0103 - mae: 0.0798 - val_loss: 0.2031 - val_mse: 0.2031 - val_mae: 0.4290 - lr: 0.0010 - 164ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss improved from 0.19748 to 0.18913, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0118 - mse: 0.0118 - mae: 0.0832 - val_loss: 0.1891 - val_mse: 0.1891 - val_mae: 0.4133 - lr: 0.0010 - 184ms/epoch - 4ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.18913
45/45 - 0s - loss: 0.0114 - mse: 0.0114 - mae: 0.0834 - val_loss: 0.1922 - val_mse: 0.1922 - val_mae: 0.4168 - lr: 0.0010 - 183ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.18913
45/45 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0880 - val_loss: 0.1994 - val_mse: 0.1994 - val_mae: 0.4249 - lr: 0.0010 - 170ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss improved from 0.18913 to 0.17686, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0126 - mse: 0.0126 - mae: 0.0862 - val_loss: 0.1769 - val_mse: 0.1769 - val_mae: 0.3988 - lr: 0.0010 - 177ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.17686
45/45 - 0s - loss: 0.0112 - mse: 0.0112 - mae: 0.0837 - val_loss: 0.1974 - val_mse: 0.1974 - val_mae: 0.4225 - lr: 0.0010 - 171ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.17686
45/45 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0861 - val_loss: 0.1792 - val_mse: 0.1792 - val_mae: 0.4008 - lr: 0.0010 - 172ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss improved from 0.17686 to 0.15253, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0111 - mse: 0.0111 - mae: 0.0824 - val_loss: 0.1525 - val_mse: 0.1525 - val_mae: 0.3675 - lr: 0.0010 - 192ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.15253
45/45 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0840 - val_loss: 0.1632 - val_mse: 0.1632 - val_mae: 0.3811 - lr: 0.0010 - 178ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.15253
45/45 - 0s - loss: 0.0109 - mse: 0.0109 - mae: 0.0833 - val_loss: 0.1910 - val_mse: 0.1910 - val_mae: 0.4138 - lr: 0.0010 - 164ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.15253
45/45 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0838 - val_loss: 0.1712 - val_mse: 0.1712 - val_mae: 0.3887 - lr: 0.0010 - 172ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.15253
45/45 - 0s - loss: 0.0094 - mse: 0.0094 - mae: 0.0781 - val_loss: 0.1718 - val_mse: 0.1718 - val_mae: 0.3894 - lr: 0.0010 - 170ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00033: val_loss did not improve from 0.15253
45/45 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0757 - val_loss: 0.1762 - val_mse: 0.1762 - val_mae: 0.3939 - lr: 0.0010 - 181ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: val_loss improved from 0.15253 to 0.14316, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0154 - mse: 0.0154 - mae: 0.1010 - val_loss: 0.1432 - val_mse: 0.1432 - val_mae: 0.3543 - lr: 1.0000e-04 - 207ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss improved from 0.14316 to 0.13220, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0585 - val_loss: 0.1322 - val_mse: 0.1322 - val_mae: 0.3398 - lr: 1.0000e-04 - 180ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss improved from 0.13220 to 0.12947, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0584 - val_loss: 0.1295 - val_mse: 0.1295 - val_mae: 0.3359 - lr: 1.0000e-04 - 190ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss improved from 0.12947 to 0.12788, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0575 - val_loss: 0.1279 - val_mse: 0.1279 - val_mae: 0.3335 - lr: 1.0000e-04 - 189ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss improved from 0.12788 to 0.12680, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0578 - val_loss: 0.1268 - val_mse: 0.1268 - val_mae: 0.3318 - lr: 1.0000e-04 - 199ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss improved from 0.12680 to 0.12636, saving model to LSTM7.h5
45/45 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0565 - val_loss: 0.1264 - val_mse: 0.1264 - val_mae: 0.3309 - lr: 1.0000e-04 - 207ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0563 - val_loss: 0.1267 - val_mse: 0.1267 - val_mae: 0.3311 - lr: 1.0000e-04 - 196ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0548 - val_loss: 0.1272 - val_mse: 0.1272 - val_mae: 0.3317 - lr: 1.0000e-04 - 181ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0527 - val_loss: 0.1292 - val_mse: 0.1292 - val_mae: 0.3343 - lr: 1.0000e-04 - 199ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0523 - val_loss: 0.1302 - val_mse: 0.1302 - val_mae: 0.3356 - lr: 1.0000e-04 - 189ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00044: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0536 - val_loss: 0.1289 - val_mse: 0.1289 - val_mae: 0.3334 - lr: 1.0000e-04 - 187ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0518 - val_loss: 0.1286 - val_mse: 0.1286 - val_mae: 0.3330 - lr: 1.0000e-05 - 172ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0526 - val_loss: 0.1282 - val_mse: 0.1282 - val_mae: 0.3324 - lr: 1.0000e-05 - 163ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0519 - val_loss: 0.1281 - val_mse: 0.1281 - val_mae: 0.3324 - lr: 1.0000e-05 - 178ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0547 - val_loss: 0.1280 - val_mse: 0.1280 - val_mae: 0.3322 - lr: 1.0000e-05 - 168ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00049: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0502 - val_loss: 0.1281 - val_mse: 0.1281 - val_mae: 0.3324 - lr: 1.0000e-05 - 188ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0529 - val_loss: 0.1283 - val_mse: 0.1283 - val_mae: 0.3325 - lr: 1.0000e-05 - 179ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0528 - val_loss: 0.1280 - val_mse: 0.1280 - val_mae: 0.3321 - lr: 1.0000e-05 - 169ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0531 - val_loss: 0.1277 - val_mse: 0.1277 - val_mae: 0.3317 - lr: 1.0000e-05 - 168ms/epoch - 4ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0524 - val_loss: 0.1280 - val_mse: 0.1280 - val_mae: 0.3321 - lr: 1.0000e-05 - 165ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0522 - val_loss: 0.1277 - val_mse: 0.1277 - val_mae: 0.3317 - lr: 1.0000e-05 - 180ms/epoch - 4ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0536 - val_loss: 0.1279 - val_mse: 0.1279 - val_mae: 0.3320 - lr: 1.0000e-05 - 186ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0517 - val_loss: 0.1281 - val_mse: 0.1281 - val_mae: 0.3323 - lr: 1.0000e-05 - 178ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0516 - val_loss: 0.1286 - val_mse: 0.1286 - val_mae: 0.3329 - lr: 1.0000e-05 - 166ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0539 - val_loss: 0.1282 - val_mse: 0.1282 - val_mae: 0.3324 - lr: 1.0000e-05 - 172ms/epoch - 4ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0509 - val_loss: 0.1283 - val_mse: 0.1283 - val_mae: 0.3325 - lr: 1.0000e-05 - 167ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0502 - val_loss: 0.1289 - val_mse: 0.1289 - val_mae: 0.3333 - lr: 1.0000e-05 - 184ms/epoch - 4ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0523 - val_loss: 0.1291 - val_mse: 0.1291 - val_mae: 0.3337 - lr: 1.0000e-05 - 178ms/epoch - 4ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0518 - val_loss: 0.1292 - val_mse: 0.1292 - val_mae: 0.3337 - lr: 1.0000e-05 - 163ms/epoch - 4ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0531 - val_loss: 0.1290 - val_mse: 0.1290 - val_mae: 0.3334 - lr: 1.0000e-05 - 163ms/epoch - 4ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0516 - val_loss: 0.1291 - val_mse: 0.1291 - val_mae: 0.3335 - lr: 1.0000e-05 - 166ms/epoch - 4ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.1291 - val_mse: 0.1291 - val_mae: 0.3335 - lr: 1.0000e-05 - 172ms/epoch - 4ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0509 - val_loss: 0.1291 - val_mse: 0.1291 - val_mae: 0.3336 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0529 - val_loss: 0.1296 - val_mse: 0.1296 - val_mae: 0.3341 - lr: 1.0000e-05 - 178ms/epoch - 4ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0519 - val_loss: 0.1294 - val_mse: 0.1294 - val_mae: 0.3338 - lr: 1.0000e-05 - 167ms/epoch - 4ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0536 - val_loss: 0.1291 - val_mse: 0.1291 - val_mae: 0.3335 - lr: 1.0000e-05 - 166ms/epoch - 4ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0523 - val_loss: 0.1292 - val_mse: 0.1292 - val_mae: 0.3336 - lr: 1.0000e-05 - 177ms/epoch - 4ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0501 - val_loss: 0.1291 - val_mse: 0.1291 - val_mae: 0.3335 - lr: 1.0000e-05 - 179ms/epoch - 4ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0505 - val_loss: 0.1294 - val_mse: 0.1294 - val_mae: 0.3338 - lr: 1.0000e-05 - 184ms/epoch - 4ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0507 - val_loss: 0.1293 - val_mse: 0.1293 - val_mae: 0.3337 - lr: 1.0000e-05 - 178ms/epoch - 4ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.1295 - val_mse: 0.1295 - val_mae: 0.3339 - lr: 1.0000e-05 - 164ms/epoch - 4ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0493 - val_loss: 0.1296 - val_mse: 0.1296 - val_mae: 0.3341 - lr: 1.0000e-05 - 162ms/epoch - 4ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0529 - val_loss: 0.1294 - val_mse: 0.1294 - val_mae: 0.3339 - lr: 1.0000e-05 - 175ms/epoch - 4ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0521 - val_loss: 0.1292 - val_mse: 0.1292 - val_mae: 0.3335 - lr: 1.0000e-05 - 175ms/epoch - 4ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0504 - val_loss: 0.1284 - val_mse: 0.1284 - val_mae: 0.3324 - lr: 1.0000e-05 - 182ms/epoch - 4ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0501 - val_loss: 0.1282 - val_mse: 0.1282 - val_mae: 0.3320 - lr: 1.0000e-05 - 166ms/epoch - 4ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.1281 - val_mse: 0.1281 - val_mae: 0.3318 - lr: 1.0000e-05 - 165ms/epoch - 4ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0491 - val_loss: 0.1279 - val_mse: 0.1279 - val_mae: 0.3316 - lr: 1.0000e-05 - 169ms/epoch - 4ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0511 - val_loss: 0.1279 - val_mse: 0.1279 - val_mae: 0.3315 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0487 - val_loss: 0.1282 - val_mse: 0.1282 - val_mae: 0.3319 - lr: 1.0000e-05 - 195ms/epoch - 4ms/step
Epoch 84/500

Epoch 00084: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0521 - val_loss: 0.1286 - val_mse: 0.1286 - val_mae: 0.3325 - lr: 1.0000e-05 - 185ms/epoch - 4ms/step
Epoch 85/500

Epoch 00085: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0501 - val_loss: 0.1293 - val_mse: 0.1293 - val_mae: 0.3334 - lr: 1.0000e-05 - 166ms/epoch - 4ms/step
Epoch 86/500

Epoch 00086: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0529 - val_loss: 0.1293 - val_mse: 0.1293 - val_mae: 0.3333 - lr: 1.0000e-05 - 168ms/epoch - 4ms/step
Epoch 87/500

Epoch 00087: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0519 - val_loss: 0.1295 - val_mse: 0.1295 - val_mae: 0.3337 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 88/500

Epoch 00088: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0531 - val_loss: 0.1290 - val_mse: 0.1290 - val_mae: 0.3329 - lr: 1.0000e-05 - 191ms/epoch - 4ms/step
Epoch 89/500

Epoch 00089: val_loss did not improve from 0.12636
45/45 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0518 - val_loss: 0.1289 - val_mse: 0.1289 - val_mae: 0.3328 - lr: 1.0000e-05 - 191ms/epoch - 4ms/step
Epoch 00089: early stopping

SMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 23.38002191723926 
RMSE:	 4.835289227878645 
MAPE:	 3.8675720673818827

EMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 35.056668726825066 
RMSE:	 5.920867227596399 
MAPE:	 4.704877912816018

WMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 44.87192646385527 
RMSE:	 6.698651092858566 
MAPE:	 5.33068935026581

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 53.079656203261706 
RMSE:	 7.285578645739933 
MAPE:	 5.726487515550782

KAMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 30.678794294842323 
RMSE:	 5.5388441298561855 
MAPE:	 4.336649130448084
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.733, Time=2.47 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.592, Time=4.30 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15587.551, Time=8.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.592, Time=5.82 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16365.334, Time=9.78 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16163.760, Time=13.81 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16245.181, Time=15.18 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17028.017, Time=5.16 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17106.133, Time=5.92 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17085.425, Time=6.90 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=-17000.553, Time=3.53 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 80.941 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood                8579.066
Date:                Sun, 12 Dec 2021   AIC                         -17106.133
Time:                        19:26:22   BIC                         -16984.171
Sample:                             0   HQIC                        -17059.294
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -3.048e-10   1.69e-20   -1.8e+10      0.000   -3.05e-10   -3.05e-10
x2         -3.042e-10   1.75e-20  -1.74e+10      0.000   -3.04e-10   -3.04e-10
x3         -3.108e-10   1.62e-20  -1.92e+10      0.000   -3.11e-10   -3.11e-10
x4             1.0000   1.69e-20   5.91e+19      0.000       1.000       1.000
x5         -2.767e-10   1.61e-20  -1.72e+10      0.000   -2.77e-10   -2.77e-10
x6         -6.072e-09   1.38e-19  -4.42e+10      0.000   -6.07e-09   -6.07e-09
x7           -2.8e-10   1.62e-20  -1.73e+10      0.000    -2.8e-10    -2.8e-10
x8         -2.792e-10   1.65e-20  -1.69e+10      0.000   -2.79e-10   -2.79e-10
x9         -1.502e-10   1.02e-21  -1.48e+11      0.000    -1.5e-10    -1.5e-10
x10        -2.482e-10    4.3e-21  -5.77e+10      0.000   -2.48e-10   -2.48e-10
x11        -2.764e-10   1.64e-20  -1.69e+10      0.000   -2.76e-10   -2.76e-10
x12        -2.857e-10   1.64e-20  -1.74e+10      0.000   -2.86e-10   -2.86e-10
x13        -2.944e-10   1.66e-20  -1.77e+10      0.000   -2.94e-10   -2.94e-10
x14        -2.403e-09   4.86e-20  -4.95e+10      0.000    -2.4e-09    -2.4e-09
x15        -3.368e-10   1.81e-20  -1.86e+10      0.000   -3.37e-10   -3.37e-10
x16        -2.169e-10   1.45e-20  -1.49e+10      0.000   -2.17e-10   -2.17e-10
x17        -2.124e-10   1.44e-20  -1.47e+10      0.000   -2.12e-10   -2.12e-10
x18        -9.125e-10   2.98e-20  -3.06e+10      0.000   -9.13e-10   -9.13e-10
x19        -3.698e-10    1.9e-20  -1.95e+10      0.000    -3.7e-10    -3.7e-10
x20          -8.9e-10   2.94e-20  -3.03e+10      0.000    -8.9e-10    -8.9e-10
x21        -1.844e-11   1.86e-22   -9.9e+10      0.000   -1.84e-11   -1.84e-11
x22        -2.169e-10   5.04e-22   -4.3e+11      0.000   -2.17e-10   -2.17e-10
ar.L1         -1.2011    7.4e-23  -1.62e+22      0.000      -1.201      -1.201
ar.L2         -0.9017   1.51e-22  -5.98e+21      0.000      -0.902      -0.902
ar.L3         -0.4014   9.48e-23  -4.23e+21      0.000      -0.401      -0.401
sigma2      8.782e-11   6.95e-11      1.264      0.206   -4.84e-11    2.24e-10
===================================================================================
Ljung-Box (L1) (Q):                   3.61   Jarque-Bera (JB):             16191.93
Prob(Q):                              0.06   Prob(JB):                         0.00
Heteroskedasticity (H):               0.35   Skew:                             0.59
Prob(H) (two-sided):                  0.00   Kurtosis:                        24.94
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 3.23e+40. Standard errors may be unstable.
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.06775, saving model to LSTM7.h5
58/58 - 2s - loss: 0.0417 - mse: 0.0417 - mae: 0.1613 - val_loss: 0.0677 - val_mse: 0.0677 - val_mae: 0.2084 - lr: 0.0010 - 2s/epoch - 39ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.06775
58/58 - 0s - loss: 0.0227 - mse: 0.0227 - mae: 0.1232 - val_loss: 0.1669 - val_mse: 0.1669 - val_mae: 0.3564 - lr: 0.0010 - 222ms/epoch - 4ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.06775
58/58 - 0s - loss: 0.0190 - mse: 0.0190 - mae: 0.1036 - val_loss: 0.0788 - val_mse: 0.0788 - val_mae: 0.2255 - lr: 0.0010 - 213ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.06775
58/58 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0705 - val_loss: 0.1947 - val_mse: 0.1947 - val_mae: 0.3957 - lr: 0.0010 - 217ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.06775 to 0.03073, saving model to LSTM7.h5
58/58 - 0s - loss: 0.0135 - mse: 0.0135 - mae: 0.0863 - val_loss: 0.0307 - val_mse: 0.0307 - val_mae: 0.1250 - lr: 0.0010 - 232ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.03073
58/58 - 0s - loss: 0.0125 - mse: 0.0125 - mae: 0.0789 - val_loss: 0.3547 - val_mse: 0.3547 - val_mae: 0.5564 - lr: 0.0010 - 209ms/epoch - 4ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.03073 to 0.02182, saving model to LSTM7.h5
58/58 - 0s - loss: 0.0246 - mse: 0.0246 - mae: 0.1162 - val_loss: 0.0218 - val_mse: 0.0218 - val_mae: 0.1275 - lr: 0.0010 - 238ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.02182
58/58 - 0s - loss: 0.0098 - mse: 0.0098 - mae: 0.0709 - val_loss: 0.3146 - val_mse: 0.3146 - val_mae: 0.5219 - lr: 0.0010 - 218ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.02182 to 0.02122, saving model to LSTM7.h5
58/58 - 0s - loss: 0.0206 - mse: 0.0206 - mae: 0.1064 - val_loss: 0.0212 - val_mse: 0.0212 - val_mae: 0.1029 - lr: 0.0010 - 221ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0637 - val_loss: 0.2012 - val_mse: 0.2012 - val_mae: 0.4063 - lr: 0.0010 - 202ms/epoch - 3ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0137 - mse: 0.0137 - mae: 0.0854 - val_loss: 0.0673 - val_mse: 0.0673 - val_mae: 0.2084 - lr: 0.0010 - 209ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0642 - val_loss: 0.1385 - val_mse: 0.1385 - val_mae: 0.3263 - lr: 0.0010 - 218ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0106 - mse: 0.0106 - mae: 0.0784 - val_loss: 0.1140 - val_mse: 0.1140 - val_mae: 0.2914 - lr: 0.0010 - 215ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00014: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0085 - mse: 0.0085 - mae: 0.0709 - val_loss: 0.1579 - val_mse: 0.1579 - val_mae: 0.3520 - lr: 0.0010 - 211ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0261 - mse: 0.0261 - mae: 0.1345 - val_loss: 0.0985 - val_mse: 0.0985 - val_mae: 0.2703 - lr: 1.0000e-04 - 209ms/epoch - 4ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0097 - mse: 0.0097 - mae: 0.0824 - val_loss: 0.0880 - val_mse: 0.0880 - val_mae: 0.2526 - lr: 1.0000e-04 - 208ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0749 - val_loss: 0.0855 - val_mse: 0.0855 - val_mae: 0.2473 - lr: 1.0000e-04 - 220ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0700 - val_loss: 0.0830 - val_mse: 0.0830 - val_mae: 0.2418 - lr: 1.0000e-04 - 209ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00019: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0678 - val_loss: 0.0853 - val_mse: 0.0853 - val_mae: 0.2453 - lr: 1.0000e-04 - 218ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0631 - val_loss: 0.0850 - val_mse: 0.0850 - val_mae: 0.2448 - lr: 1.0000e-05 - 208ms/epoch - 4ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0602 - val_loss: 0.0849 - val_mse: 0.0849 - val_mae: 0.2445 - lr: 1.0000e-05 - 222ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0636 - val_loss: 0.0847 - val_mse: 0.0847 - val_mae: 0.2443 - lr: 1.0000e-05 - 224ms/epoch - 4ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0615 - val_loss: 0.0844 - val_mse: 0.0844 - val_mae: 0.2436 - lr: 1.0000e-05 - 208ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00024: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0595 - val_loss: 0.0842 - val_mse: 0.0842 - val_mae: 0.2433 - lr: 1.0000e-05 - 217ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0625 - val_loss: 0.0843 - val_mse: 0.0843 - val_mae: 0.2434 - lr: 1.0000e-05 - 210ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0639 - val_loss: 0.0839 - val_mse: 0.0839 - val_mae: 0.2427 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0605 - val_loss: 0.0838 - val_mse: 0.0838 - val_mae: 0.2424 - lr: 1.0000e-05 - 209ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0630 - val_loss: 0.0835 - val_mse: 0.0835 - val_mae: 0.2418 - lr: 1.0000e-05 - 208ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0606 - val_loss: 0.0837 - val_mse: 0.0837 - val_mae: 0.2421 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0619 - val_loss: 0.0838 - val_mse: 0.0838 - val_mae: 0.2422 - lr: 1.0000e-05 - 220ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0593 - val_loss: 0.0843 - val_mse: 0.0843 - val_mae: 0.2430 - lr: 1.0000e-05 - 217ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0615 - val_loss: 0.0844 - val_mse: 0.0844 - val_mae: 0.2431 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0616 - val_loss: 0.0846 - val_mse: 0.0846 - val_mae: 0.2434 - lr: 1.0000e-05 - 207ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0599 - val_loss: 0.0850 - val_mse: 0.0850 - val_mae: 0.2442 - lr: 1.0000e-05 - 207ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0587 - val_loss: 0.0853 - val_mse: 0.0853 - val_mae: 0.2445 - lr: 1.0000e-05 - 205ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0586 - val_loss: 0.0852 - val_mse: 0.0852 - val_mae: 0.2442 - lr: 1.0000e-05 - 219ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0603 - val_loss: 0.0853 - val_mse: 0.0853 - val_mae: 0.2443 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0621 - val_loss: 0.0853 - val_mse: 0.0853 - val_mae: 0.2442 - lr: 1.0000e-05 - 208ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0593 - val_loss: 0.0855 - val_mse: 0.0855 - val_mae: 0.2445 - lr: 1.0000e-05 - 211ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0585 - val_loss: 0.0854 - val_mse: 0.0854 - val_mae: 0.2441 - lr: 1.0000e-05 - 219ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0583 - val_loss: 0.0852 - val_mse: 0.0852 - val_mae: 0.2436 - lr: 1.0000e-05 - 211ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0602 - val_loss: 0.0856 - val_mse: 0.0856 - val_mae: 0.2444 - lr: 1.0000e-05 - 209ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0586 - val_loss: 0.0860 - val_mse: 0.0860 - val_mae: 0.2450 - lr: 1.0000e-05 - 217ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0589 - val_loss: 0.0863 - val_mse: 0.0863 - val_mae: 0.2453 - lr: 1.0000e-05 - 212ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0569 - val_loss: 0.0865 - val_mse: 0.0865 - val_mae: 0.2456 - lr: 1.0000e-05 - 209ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0583 - val_loss: 0.0873 - val_mse: 0.0873 - val_mae: 0.2470 - lr: 1.0000e-05 - 206ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0600 - val_loss: 0.0879 - val_mse: 0.0879 - val_mae: 0.2479 - lr: 1.0000e-05 - 211ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0600 - val_loss: 0.0883 - val_mse: 0.0883 - val_mae: 0.2485 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.0889 - val_mse: 0.0889 - val_mae: 0.2495 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0564 - val_loss: 0.0892 - val_mse: 0.0892 - val_mae: 0.2499 - lr: 1.0000e-05 - 218ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0567 - val_loss: 0.0899 - val_mse: 0.0899 - val_mae: 0.2510 - lr: 1.0000e-05 - 212ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0581 - val_loss: 0.0899 - val_mse: 0.0899 - val_mae: 0.2510 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0560 - val_loss: 0.0901 - val_mse: 0.0901 - val_mae: 0.2511 - lr: 1.0000e-05 - 218ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0583 - val_loss: 0.0903 - val_mse: 0.0903 - val_mae: 0.2515 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0593 - val_loss: 0.0903 - val_mse: 0.0903 - val_mae: 0.2513 - lr: 1.0000e-05 - 211ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0561 - val_loss: 0.0902 - val_mse: 0.0902 - val_mae: 0.2510 - lr: 1.0000e-05 - 207ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0564 - val_loss: 0.0902 - val_mse: 0.0902 - val_mae: 0.2510 - lr: 1.0000e-05 - 208ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0576 - val_loss: 0.0911 - val_mse: 0.0911 - val_mae: 0.2524 - lr: 1.0000e-05 - 210ms/epoch - 4ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.02122
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0577 - val_loss: 0.0920 - val_mse: 0.0920 - val_mae: 0.2538 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 00059: early stopping

SMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 23.38002191723926 
RMSE:	 4.835289227878645 
MAPE:	 3.8675720673818827

EMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 35.056668726825066 
RMSE:	 5.920867227596399 
MAPE:	 4.704877912816018

WMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 44.87192646385527 
RMSE:	 6.698651092858566 
MAPE:	 5.33068935026581

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 53.079656203261706 
RMSE:	 7.285578645739933 
MAPE:	 5.726487515550782

KAMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 30.678794294842323 
RMSE:	 5.5388441298561855 
MAPE:	 4.336649130448084

MIDPOINT
Prediction vs Close:		47.39% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 19.38951232132957 
RMSE:	 4.4033523957695655 
MAPE:	 3.5042510250586574
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16954.347, Time=2.59 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14725.736, Time=2.38 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16732.390, Time=8.17 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15913.358, Time=7.22 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16550.077, Time=10.03 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15004.835, Time=9.43 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16027.273, Time=10.03 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-16934.995, Time=2.56 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16924.758, Time=3.21 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=-16952.347, Time=2.17 sec

Best model:  ARIMA(1,3,1)(0,0,0)[0]          
Total fit time: 57.809 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 1)   Log Likelihood                8502.173
Date:                Sun, 12 Dec 2021   AIC                         -16954.347
Time:                        19:29:15   BIC                         -16837.076
Sample:                             0   HQIC                        -16909.310
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1          3.409e-14   2.62e-06    1.3e-08      1.000   -5.13e-06    5.13e-06
x2          1.816e-14   2.62e-06   6.93e-09      1.000   -5.13e-06    5.13e-06
x3         -2.039e-15   2.47e-06  -8.26e-10      1.000   -4.84e-06    4.84e-06
x4             1.0000    2.5e-06      4e+05      0.000       1.000       1.000
x5          2.488e-12   2.48e-06      1e-06      1.000   -4.86e-06    4.86e-06
x6           2.84e-15   6.48e-06   4.38e-10      1.000   -1.27e-05    1.27e-05
x7          3.618e-13   3.24e-06   1.12e-07      1.000   -6.36e-06    6.36e-06
x8            -0.0002   4.44e-06    -43.079      0.000      -0.000      -0.000
x9           2.93e-14    6.3e-08   4.65e-07      1.000   -1.23e-07    1.23e-07
x10        -2.843e-05   9.63e-06     -2.951      0.003   -4.73e-05   -9.55e-06
x11            0.0002   3.28e-06     53.981      0.000       0.000       0.000
x12            0.0001   5.63e-06     23.078      0.000       0.000       0.000
x13        -2.595e-14   2.63e-06  -9.88e-09      1.000   -5.15e-06    5.15e-06
x14        -6.497e-14   5.76e-06  -1.13e-08      1.000   -1.13e-05    1.13e-05
x15         1.699e-12   3.08e-06   5.51e-07      1.000   -6.04e-06    6.04e-06
x16        -3.969e-12   4.77e-06  -8.33e-07      1.000   -9.34e-06    9.34e-06
x17         5.452e-12   8.58e-07   6.35e-06      1.000   -1.68e-06    1.68e-06
x18         -3.68e-13   1.33e-05  -2.76e-08      1.000   -2.61e-05    2.61e-05
x19        -5.643e-13   4.61e-06  -1.22e-07      1.000   -9.03e-06    9.03e-06
x20         6.651e-14    4.9e-05   1.36e-09      1.000   -9.61e-05    9.61e-05
x21         -1.76e-16   8.47e-11  -2.08e-06      1.000   -1.66e-10    1.66e-10
x22         -7.82e-16   1.75e-10  -4.47e-06      1.000   -3.43e-10    3.43e-10
ar.L1         -0.2858   5.46e-08  -5.24e+06      0.000      -0.286      -0.286
ma.L1         -0.9143   5.59e-08  -1.63e+07      0.000      -0.914      -0.914
sigma2          1e-10   6.99e-11      1.430      0.153   -3.71e-11    2.37e-10
===================================================================================
Ljung-Box (L1) (Q):                  84.00   Jarque-Bera (JB):           4822228.07
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            -6.05
Prob(H) (two-sided):                  0.00   Kurtosis:                       381.97
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 3.54e+27. Standard errors may be unstable.
ARIMA order: (1, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.36626, saving model to LSTM7.h5
43/43 - 2s - loss: 0.3061 - mse: 0.3061 - mae: 0.3860 - val_loss: 0.3663 - val_mse: 0.3663 - val_mae: 0.5814 - lr: 0.0010 - 2s/epoch - 54ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.36626 to 0.16105, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0369 - mse: 0.0369 - mae: 0.1521 - val_loss: 0.1611 - val_mse: 0.1611 - val_mae: 0.3788 - lr: 0.0010 - 170ms/epoch - 4ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.16105 to 0.09031, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0220 - mse: 0.0220 - mae: 0.1203 - val_loss: 0.0903 - val_mse: 0.0903 - val_mae: 0.2761 - lr: 0.0010 - 172ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.09031 to 0.07747, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0176 - mse: 0.0176 - mae: 0.1051 - val_loss: 0.0775 - val_mse: 0.0775 - val_mae: 0.2534 - lr: 0.0010 - 195ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.07747
43/43 - 0s - loss: 0.0162 - mse: 0.0162 - mae: 0.1023 - val_loss: 0.0849 - val_mse: 0.0849 - val_mae: 0.2668 - lr: 0.0010 - 190ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.07747 to 0.07631, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0138 - mse: 0.0138 - mae: 0.0938 - val_loss: 0.0763 - val_mse: 0.0763 - val_mae: 0.2512 - lr: 0.0010 - 197ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.07631
43/43 - 0s - loss: 0.0129 - mse: 0.0129 - mae: 0.0902 - val_loss: 0.0773 - val_mse: 0.0773 - val_mae: 0.2534 - lr: 0.0010 - 168ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.07631 to 0.07038, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0149 - mse: 0.0149 - mae: 0.0985 - val_loss: 0.0704 - val_mse: 0.0704 - val_mae: 0.2405 - lr: 0.0010 - 170ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.07038
43/43 - 0s - loss: 0.0143 - mse: 0.0143 - mae: 0.0962 - val_loss: 0.0727 - val_mse: 0.0727 - val_mae: 0.2453 - lr: 0.0010 - 171ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.07038
43/43 - 0s - loss: 0.0143 - mse: 0.0143 - mae: 0.0972 - val_loss: 0.0707 - val_mse: 0.0707 - val_mae: 0.2414 - lr: 0.0010 - 186ms/epoch - 4ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.07038 to 0.06790, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0140 - mse: 0.0140 - mae: 0.0952 - val_loss: 0.0679 - val_mse: 0.0679 - val_mae: 0.2355 - lr: 0.0010 - 192ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.06790 to 0.06263, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0118 - mse: 0.0118 - mae: 0.0866 - val_loss: 0.0626 - val_mse: 0.0626 - val_mae: 0.2248 - lr: 0.0010 - 189ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.06263 to 0.04913, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0125 - mse: 0.0125 - mae: 0.0907 - val_loss: 0.0491 - val_mse: 0.0491 - val_mae: 0.1955 - lr: 0.0010 - 190ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.04913 to 0.04302, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0126 - mse: 0.0126 - mae: 0.0913 - val_loss: 0.0430 - val_mse: 0.0430 - val_mae: 0.1808 - lr: 0.0010 - 175ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04302
43/43 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0925 - val_loss: 0.0585 - val_mse: 0.0585 - val_mae: 0.2157 - lr: 0.0010 - 185ms/epoch - 4ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.04302
43/43 - 0s - loss: 0.0122 - mse: 0.0122 - mae: 0.0908 - val_loss: 0.0491 - val_mse: 0.0491 - val_mae: 0.1950 - lr: 0.0010 - 187ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04302
43/43 - 0s - loss: 0.0112 - mse: 0.0112 - mae: 0.0870 - val_loss: 0.0518 - val_mse: 0.0518 - val_mae: 0.2009 - lr: 0.0010 - 178ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04302
43/43 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0847 - val_loss: 0.0529 - val_mse: 0.0529 - val_mae: 0.2033 - lr: 0.0010 - 170ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00019: val_loss did not improve from 0.04302
43/43 - 0s - loss: 0.0098 - mse: 0.0098 - mae: 0.0795 - val_loss: 0.0513 - val_mse: 0.0513 - val_mae: 0.1997 - lr: 0.0010 - 160ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.04302 to 0.04016, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0137 - mse: 0.0137 - mae: 0.0944 - val_loss: 0.0402 - val_mse: 0.0402 - val_mae: 0.1725 - lr: 1.0000e-04 - 194ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.04016 to 0.03663, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0637 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1631 - lr: 1.0000e-04 - 200ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss improved from 0.03663 to 0.03522, saving model to LSTM7.h5
43/43 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0601 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1593 - lr: 1.0000e-04 - 195ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0582 - val_loss: 0.0357 - val_mse: 0.0357 - val_mae: 0.1604 - lr: 1.0000e-04 - 163ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0591 - val_loss: 0.0365 - val_mse: 0.0365 - val_mae: 0.1625 - lr: 1.0000e-04 - 160ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0579 - val_loss: 0.0372 - val_mse: 0.0372 - val_mae: 0.1642 - lr: 1.0000e-04 - 167ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0611 - val_loss: 0.0374 - val_mse: 0.0374 - val_mae: 0.1647 - lr: 1.0000e-04 - 183ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00027: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0562 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1620 - lr: 1.0000e-04 - 184ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0579 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1620 - lr: 1.0000e-05 - 175ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0569 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1620 - lr: 1.0000e-05 - 170ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0544 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1619 - lr: 1.0000e-05 - 160ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0581 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1620 - lr: 1.0000e-05 - 184ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00032: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0558 - val_loss: 0.0363 - val_mse: 0.0363 - val_mae: 0.1619 - lr: 1.0000e-05 - 186ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0577 - val_loss: 0.0363 - val_mse: 0.0363 - val_mae: 0.1618 - lr: 1.0000e-05 - 178ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0572 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1620 - lr: 1.0000e-05 - 165ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.0365 - val_mse: 0.0365 - val_mae: 0.1622 - lr: 1.0000e-05 - 158ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0573 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1626 - lr: 1.0000e-05 - 163ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0557 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1632 - lr: 1.0000e-05 - 185ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1630 - lr: 1.0000e-05 - 184ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0564 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1629 - lr: 1.0000e-05 - 180ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0556 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1629 - lr: 1.0000e-05 - 173ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0526 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1628 - lr: 1.0000e-05 - 175ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0570 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1627 - lr: 1.0000e-05 - 167ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0558 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1629 - lr: 1.0000e-05 - 187ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0545 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1631 - lr: 1.0000e-05 - 177ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0558 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1630 - lr: 1.0000e-05 - 160ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0574 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1630 - lr: 1.0000e-05 - 168ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0557 - val_loss: 0.0369 - val_mse: 0.0369 - val_mae: 0.1633 - lr: 1.0000e-05 - 160ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0553 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1630 - lr: 1.0000e-05 - 182ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0563 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1634 - lr: 1.0000e-05 - 187ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.0371 - val_mse: 0.0371 - val_mae: 0.1637 - lr: 1.0000e-05 - 176ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0577 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1637 - lr: 1.0000e-05 - 161ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0512 - val_loss: 0.0371 - val_mse: 0.0371 - val_mae: 0.1638 - lr: 1.0000e-05 - 159ms/epoch - 4ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0574 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1635 - lr: 1.0000e-05 - 178ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0541 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1634 - lr: 1.0000e-05 - 189ms/epoch - 4ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0555 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1629 - lr: 1.0000e-05 - 188ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0549 - val_loss: 0.0365 - val_mse: 0.0365 - val_mae: 0.1623 - lr: 1.0000e-05 - 166ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0553 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1624 - lr: 1.0000e-05 - 172ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0554 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1626 - lr: 1.0000e-05 - 176ms/epoch - 4ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0577 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1624 - lr: 1.0000e-05 - 188ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0550 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1624 - lr: 1.0000e-05 - 183ms/epoch - 4ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0555 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1627 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0580 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1625 - lr: 1.0000e-05 - 164ms/epoch - 4ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0583 - val_loss: 0.0365 - val_mse: 0.0365 - val_mae: 0.1620 - lr: 1.0000e-05 - 169ms/epoch - 4ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0564 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1623 - lr: 1.0000e-05 - 179ms/epoch - 4ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0558 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1630 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1629 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0564 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1625 - lr: 1.0000e-05 - 167ms/epoch - 4ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0561 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1628 - lr: 1.0000e-05 - 166ms/epoch - 4ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.0371 - val_mse: 0.0371 - val_mae: 0.1638 - lr: 1.0000e-05 - 155ms/epoch - 4ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0560 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1634 - lr: 1.0000e-05 - 174ms/epoch - 4ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1627 - lr: 1.0000e-05 - 183ms/epoch - 4ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.03522
43/43 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0550 - val_loss: 0.0365 - val_mse: 0.0365 - val_mae: 0.1622 - lr: 1.0000e-05 - 180ms/epoch - 4ms/step
Epoch 00072: early stopping

SMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 23.38002191723926 
RMSE:	 4.835289227878645 
MAPE:	 3.8675720673818827

EMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 35.056668726825066 
RMSE:	 5.920867227596399 
MAPE:	 4.704877912816018

WMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 44.87192646385527 
RMSE:	 6.698651092858566 
MAPE:	 5.33068935026581

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 53.079656203261706 
RMSE:	 7.285578645739933 
MAPE:	 5.726487515550782

KAMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 30.678794294842323 
RMSE:	 5.5388441298561855 
MAPE:	 4.336649130448084

MIDPOINT
Prediction vs Close:		47.39% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 19.38951232132957 
RMSE:	 4.4033523957695655 
MAPE:	 3.5042510250586574

T3
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	52.61% Accuracy
MSE:	 90.72292612095576 
RMSE:	 9.524858325505727 
MAPE:	 7.398189805001564
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16412.930, Time=11.04 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14867.265, Time=6.57 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15902.803, Time=5.52 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15117.003, Time=8.07 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15669.652, Time=8.03 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-12676.374, Time=9.01 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16418.724, Time=9.01 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-15107.772, Time=15.03 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15708.742, Time=16.14 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-13418.641, Time=25.03 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 113.483 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8234.362
Date:                Sun, 12 Dec 2021   AIC                         -16418.724
Time:                        19:34:17   BIC                         -16301.453
Sample:                             0   HQIC                        -16373.687
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -1.784e-07      0.001     -0.000      1.000      -0.002       0.002
x2         -1.784e-07      0.001     -0.000      1.000      -0.003       0.003
x3         -1.794e-07      0.001     -0.000      1.000      -0.002       0.002
x4             1.0000      0.000   2616.546      0.000       0.999       1.001
x5         -1.704e-07      0.000     -0.000      1.000      -0.001       0.001
x6         -2.858e-07   3.31e-05     -0.009      0.993   -6.52e-05    6.46e-05
x7         -1.754e-07      0.001     -0.000      1.000      -0.002       0.002
x8             0.0007      0.000      3.091      0.002       0.000       0.001
x9          3.313e-08      0.000   9.39e-05      1.000      -0.001       0.001
x10         3.499e-06      0.000      0.022      0.983      -0.000       0.000
x11           -0.0003      0.000     -1.284      0.199      -0.001       0.000
x12        -6.362e-05      0.000     -0.260      0.795      -0.001       0.000
x13        -1.783e-07      0.000     -0.001      0.999      -0.000       0.000
x14        -5.244e-07      0.001     -0.001      0.999      -0.001       0.001
x15        -1.737e-07      0.000     -0.001      0.999      -0.000       0.000
x16        -2.583e-07      0.000     -0.001      0.999      -0.000       0.000
x17         -1.74e-07      0.000     -0.001      0.999      -0.000       0.000
x18        -5.776e-08      0.000     -0.000      1.000      -0.000       0.000
x19         -1.95e-07      0.000     -0.002      0.999      -0.000       0.000
x20          1.72e-07      0.000      0.001      0.999      -0.000       0.000
x21        -7.548e-10      0.001  -9.93e-07      1.000      -0.001       0.001
x22        -1.194e-08      0.000  -8.47e-05      1.000      -0.000       0.000
ma.L1         -1.3862   1.58e-05  -8.78e+04      0.000      -1.386      -1.386
ma.L2          0.4019   4.28e-05   9396.834      0.000       0.402       0.402
sigma2      1.265e-10   7.58e-11      1.669      0.095    -2.2e-11    2.75e-10
===================================================================================
Ljung-Box (L1) (Q):                  66.79   Jarque-Bera (JB):           5900482.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                           -11.32
Prob(H) (two-sided):                  0.00   Kurtosis:                       421.81
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.07e+19. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.14359, saving model to LSTM7.h5
90/90 - 3s - loss: 0.1641 - mse: 0.1641 - mae: 0.2540 - val_loss: 0.1436 - val_mse: 0.1436 - val_mae: 0.3518 - lr: 0.0010 - 3s/epoch - 28ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.14359 to 0.01378, saving model to LSTM7.h5
90/90 - 0s - loss: 0.0215 - mse: 0.0215 - mae: 0.1169 - val_loss: 0.0138 - val_mse: 0.0138 - val_mae: 0.0975 - lr: 0.0010 - 333ms/epoch - 4ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.01378 to 0.01057, saving model to LSTM7.h5
90/90 - 0s - loss: 0.0108 - mse: 0.0108 - mae: 0.0822 - val_loss: 0.0106 - val_mse: 0.0106 - val_mae: 0.0842 - lr: 0.0010 - 379ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.01057 to 0.00694, saving model to LSTM7.h5
90/90 - 0s - loss: 0.0104 - mse: 0.0104 - mae: 0.0785 - val_loss: 0.0069 - val_mse: 0.0069 - val_mae: 0.0660 - lr: 0.0010 - 347ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.00694 to 0.00690, saving model to LSTM7.h5
90/90 - 0s - loss: 0.0115 - mse: 0.0115 - mae: 0.0829 - val_loss: 0.0069 - val_mse: 0.0069 - val_mae: 0.0639 - lr: 0.0010 - 325ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0115 - mse: 0.0115 - mae: 0.0830 - val_loss: 0.0186 - val_mse: 0.0186 - val_mae: 0.1160 - lr: 0.0010 - 359ms/epoch - 4ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0100 - mse: 0.0100 - mae: 0.0769 - val_loss: 0.0171 - val_mse: 0.0171 - val_mae: 0.1096 - lr: 0.0010 - 321ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0106 - mse: 0.0106 - mae: 0.0792 - val_loss: 0.0508 - val_mse: 0.0508 - val_mae: 0.2100 - lr: 0.0010 - 334ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00009: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0100 - mse: 0.0100 - mae: 0.0756 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1702 - lr: 0.0010 - 360ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0123 - mse: 0.0123 - mae: 0.0882 - val_loss: 0.0213 - val_mse: 0.0213 - val_mae: 0.1270 - lr: 1.0000e-04 - 319ms/epoch - 4ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0627 - val_loss: 0.0222 - val_mse: 0.0222 - val_mae: 0.1296 - lr: 1.0000e-04 - 333ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0587 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1362 - lr: 1.0000e-04 - 362ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0579 - val_loss: 0.0298 - val_mse: 0.0298 - val_mae: 0.1534 - lr: 1.0000e-04 - 318ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00014: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0561 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1636 - lr: 1.0000e-04 - 324ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0568 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1623 - lr: 1.0000e-05 - 356ms/epoch - 4ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0569 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1613 - lr: 1.0000e-05 - 330ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0543 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1607 - lr: 1.0000e-05 - 326ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0564 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1605 - lr: 1.0000e-05 - 354ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00019: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0537 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1613 - lr: 1.0000e-05 - 324ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0557 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1611 - lr: 1.0000e-05 - 344ms/epoch - 4ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1617 - lr: 1.0000e-05 - 353ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0542 - val_loss: 0.0330 - val_mse: 0.0330 - val_mae: 0.1629 - lr: 1.0000e-05 - 314ms/epoch - 3ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0523 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1644 - lr: 1.0000e-05 - 340ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0549 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1657 - lr: 1.0000e-05 - 372ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0556 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1665 - lr: 1.0000e-05 - 338ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0519 - val_loss: 0.0351 - val_mse: 0.0351 - val_mae: 0.1686 - lr: 1.0000e-05 - 355ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0546 - val_loss: 0.0358 - val_mse: 0.0358 - val_mae: 0.1704 - lr: 1.0000e-05 - 345ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1720 - lr: 1.0000e-05 - 311ms/epoch - 3ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0548 - val_loss: 0.0373 - val_mse: 0.0373 - val_mae: 0.1744 - lr: 1.0000e-05 - 357ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0530 - val_loss: 0.0380 - val_mse: 0.0380 - val_mae: 0.1763 - lr: 1.0000e-05 - 338ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0554 - val_loss: 0.0391 - val_mse: 0.0391 - val_mae: 0.1790 - lr: 1.0000e-05 - 323ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0543 - val_loss: 0.0391 - val_mse: 0.0391 - val_mae: 0.1789 - lr: 1.0000e-05 - 364ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0545 - val_loss: 0.0400 - val_mse: 0.0400 - val_mae: 0.1812 - lr: 1.0000e-05 - 341ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0536 - val_loss: 0.0407 - val_mse: 0.0407 - val_mae: 0.1830 - lr: 1.0000e-05 - 330ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0535 - val_loss: 0.0413 - val_mse: 0.0413 - val_mae: 0.1846 - lr: 1.0000e-05 - 359ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0553 - val_loss: 0.0421 - val_mse: 0.0421 - val_mae: 0.1865 - lr: 1.0000e-05 - 340ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0540 - val_loss: 0.0430 - val_mse: 0.0430 - val_mae: 0.1887 - lr: 1.0000e-05 - 332ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0524 - val_loss: 0.0440 - val_mse: 0.0440 - val_mae: 0.1910 - lr: 1.0000e-05 - 344ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0532 - val_loss: 0.0445 - val_mse: 0.0445 - val_mae: 0.1924 - lr: 1.0000e-05 - 323ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0506 - val_loss: 0.0465 - val_mse: 0.0465 - val_mae: 0.1969 - lr: 1.0000e-05 - 327ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0536 - val_loss: 0.0467 - val_mse: 0.0467 - val_mae: 0.1973 - lr: 1.0000e-05 - 362ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0518 - val_loss: 0.0468 - val_mse: 0.0468 - val_mae: 0.1976 - lr: 1.0000e-05 - 316ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0538 - val_loss: 0.0472 - val_mse: 0.0472 - val_mae: 0.1986 - lr: 1.0000e-05 - 321ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0547 - val_loss: 0.0486 - val_mse: 0.0486 - val_mae: 0.2017 - lr: 1.0000e-05 - 360ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.0492 - val_mse: 0.0492 - val_mae: 0.2030 - lr: 1.0000e-05 - 320ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0543 - val_loss: 0.0481 - val_mse: 0.0481 - val_mae: 0.2004 - lr: 1.0000e-05 - 325ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0526 - val_loss: 0.0491 - val_mse: 0.0491 - val_mae: 0.2026 - lr: 1.0000e-05 - 354ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0519 - val_loss: 0.0508 - val_mse: 0.0508 - val_mae: 0.2065 - lr: 1.0000e-05 - 314ms/epoch - 3ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0516 - val_loss: 0.0525 - val_mse: 0.0525 - val_mae: 0.2103 - lr: 1.0000e-05 - 336ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0483 - val_loss: 0.0535 - val_mse: 0.0535 - val_mae: 0.2125 - lr: 1.0000e-05 - 356ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0533 - val_loss: 0.0545 - val_mse: 0.0545 - val_mae: 0.2148 - lr: 1.0000e-05 - 320ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0528 - val_loss: 0.0560 - val_mse: 0.0560 - val_mae: 0.2180 - lr: 1.0000e-05 - 327ms/epoch - 4ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0524 - val_loss: 0.0563 - val_mse: 0.0563 - val_mae: 0.2185 - lr: 1.0000e-05 - 355ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0526 - val_loss: 0.0565 - val_mse: 0.0565 - val_mae: 0.2189 - lr: 1.0000e-05 - 318ms/epoch - 4ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00690
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0529 - val_loss: 0.0576 - val_mse: 0.0576 - val_mae: 0.2210 - lr: 1.0000e-05 - 338ms/epoch - 4ms/step
Epoch 00055: early stopping

SMA
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	52.24% Accuracy
MSE:	 23.38002191723926 
RMSE:	 4.835289227878645 
MAPE:	 3.8675720673818827

EMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 35.056668726825066 
RMSE:	 5.920867227596399 
MAPE:	 4.704877912816018

WMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 44.87192646385527 
RMSE:	 6.698651092858566 
MAPE:	 5.33068935026581

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 53.079656203261706 
RMSE:	 7.285578645739933 
MAPE:	 5.726487515550782

KAMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 30.678794294842323 
RMSE:	 5.5388441298561855 
MAPE:	 4.336649130448084

MIDPOINT
Prediction vs Close:		47.39% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 19.38951232132957 
RMSE:	 4.4033523957695655 
MAPE:	 3.5042510250586574

T3
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	52.61% Accuracy
MSE:	 90.72292612095576 
RMSE:	 9.524858325505727 
MAPE:	 7.398189805001564

TEMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 46.925505559638836 
RMSE:	 6.850219380402268 
MAPE:	 5.67920042842036
Runtime: mins: 46.20308623633333

Architecture Used

In [ ]:
from google.colab import files
import cv2
uploaded = files.upload()
Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to enable. 
Saving Experiment7.png to Experiment7 (2).png
In [ ]:
img = cv2.imread('Experiment7.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)
Out[ ]:
<matplotlib.image.AxesImage at 0x7fcea03e3f10>

Model Plots

In [111]:
with open('simulation7_data.json') as json_file:
    simulation7 = json.load(json_file)
fileimg = 'Experiment7'
In [112]:
for i in range(len(list(simulation7.keys()))):
  SIM = list(simulation7.keys())[i]
  plot_train(simulation7,SIM)
  plot_test(simulation7,SIM)

----- Train RMSE for SMA ----- 8.83785474825473
----- Train_MSE_LSTM for SMA ----- 78.10767655124866
----- Train MAE LSTM for SMA ----- 7.7078387567054225

----- Test RMSE for SMA----- 4.835289227878645
----- Test_MSE_LSTM for SMA----- 23.38002191723926
----- Test_MAE_LSTM for SMA----- 3.8675720673818827

----- Train RMSE for EMA ----- 10.650301459792807
----- Train_MSE_LSTM for EMA ----- 113.4289211844648
----- Train MAE LSTM for EMA ----- 9.515306107312588

----- Test RMSE for EMA----- 5.920867227596399
----- Test_MSE_LSTM for EMA----- 35.056668726825066
----- Test_MAE_LSTM for EMA----- 4.704877912816018

----- Train RMSE for WMA ----- 11.243993898135981
----- Train_MSE_LSTM for WMA ----- 126.4273987813192
----- Train MAE LSTM for WMA ----- 10.26125688382452

----- Test RMSE for WMA----- 6.698651092858566
----- Test_MSE_LSTM for WMA----- 44.87192646385527
----- Test_MAE_LSTM for WMA----- 5.33068935026581

----- Train RMSE for DEMA ----- 12.733126101758637
----- Train_MSE_LSTM for DEMA ----- 162.1325003232871
----- Train MAE LSTM for DEMA ----- 11.568946368623488

----- Test RMSE for DEMA----- 7.285578645739933
----- Test_MSE_LSTM for DEMA----- 53.079656203261706
----- Test_MAE_LSTM for DEMA----- 5.726487515550782

----- Train RMSE for KAMA ----- 10.74346361354885
----- Train_MSE_LSTM for KAMA ----- 115.42201041564812
----- Train MAE LSTM for KAMA ----- 9.724765787837049

----- Test RMSE for KAMA----- 5.5388441298561855
----- Test_MSE_LSTM for KAMA----- 30.678794294842323
----- Test_MAE_LSTM for KAMA----- 4.336649130448084

----- Train RMSE for MIDPOINT ----- 9.390036890135665
----- Train_MSE_LSTM for MIDPOINT ----- 88.17279279810867
----- Train MAE LSTM for MIDPOINT ----- 8.334413877029046

----- Test RMSE for MIDPOINT----- 4.4033523957695655
----- Test_MSE_LSTM for MIDPOINT----- 19.38951232132957
----- Test_MAE_LSTM for MIDPOINT----- 3.5042510250586574

----- Train RMSE for T3 ----- 12.38034945262767
----- Train_MSE_LSTM for T3 ----- 153.27305256917825
----- Train MAE LSTM for T3 ----- 11.240396228217806

----- Test RMSE for T3----- 9.524858325505727
----- Test_MSE_LSTM for T3----- 90.72292612095576
----- Test_MAE_LSTM for T3----- 7.398189805001564

----- Train RMSE for TEMA ----- 7.385672398559769
----- Train_MSE_LSTM for TEMA ----- 54.548156778847606
----- Train MAE LSTM for TEMA ----- 5.039816631869549

----- Test RMSE for TEMA----- 6.850219380402268
----- Test_MSE_LSTM for TEMA----- 46.925505559638836
----- Test_MAE_LSTM for TEMA----- 5.67920042842036

Arima w Exogenous Variable Multistep MutiVariate LSTM Hybrid Model Experiment 8

In [ ]:
def get_arima_exog(dataframe,original_data, train_len, test_len):    
    

    # prepare train and test data for exogenous vr
    X_value = pd.DataFrame(low_vol.iloc[:, :])
    y_value = pd.DataFrame(low_vol.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    X_scale_dataset = X_scaler.fit_transform(X_value)
    y_scale_dataset = y_scaler.fit_transform(y_value)
    # Get data and check shape
    # X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X_scale_dataset)
    y_train, y_test, = split_train_test(y_scale_dataset)
    yc_train,yc_test = split_train_test(low_vol_data)
    yc = yc_test.values.tolist()
    y_train_list = y_train.flatten().tolist()
    y_test_list = y_test.flatten().tolist()
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

    # Initialize model
    model = auto_arima(y_train_list,exogenous  = X_train,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
            suppress_warnings=True,stepwise=True,seasonal=True)

      # Determine model parameters
    print(model.summary())
    model.fit(y_train_list,maxiter=200)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

      # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
        model = pmdarima.ARIMA(order=order)
        model.fit(y_train_list)
        # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')

        prediction.append(model.predict()[0])
        y_train_list.append(y_test_list[i])

    predictionte = y_scaler.inverse_transform(np.array(prediction).reshape(-1,1))
    y_test_ = y_scaler.inverse_transform(np.array(y_test_list).reshape(-1,1))

    # Generate error data
    mse = mean_squared_error(yc_test, predictionte)
    rmse = mse ** 0.5
    mae = mean_absolute_error(y_test_ , predictionte )
    return yc,predictionte.flatten().tolist(), mse, rmse, mae
In [ ]:
def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det =20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM7.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma+' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 3
    # define custom activation
    # 
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM7.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma+' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # #Option 4
    # # Set up & fit LSTM RNN
    model = Sequential()
    model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(input_dim, feature_size)))
    model.add(LSTM(units=int(lstm_len/2)))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='mean_squared_error', optimizer='adam')
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM8.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te
In [ ]:
if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation8 = {}
    imgfile = 'Experiment8'
    for ma in optimized_period:
                print(ma)
                print(functions[ma])
                print ( int( optimized_period[ma]))
              # if ma == 'SMA':
                low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
                low_vol = low_vol.fillna(0)
                low_vol_data = df['close']
                high_vol = pd.DataFrame()
                df2 = df.copy()
                for i in df2.columns:
                  if i in low_vol.columns:
                    high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
                high_vol_data = df['close']
                ## *****************************************************
                # Generate ARIMA and LSTM predictions
                print('\nWorking on ' + ma + ' predictions')
                try:
                  print('parameters used : ', train_len, test_len)
                  low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima_exog(low_vol,low_vol_data, train_len, test_len)
                except:
                    print('ARIMA error, skipping to next MA type')
                    continue
                Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
                final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
                mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
                rmse_ftr = mse_ftr ** 0.5
                mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
                mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

                final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
                mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
                rmse = mse ** 0.5
                mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                # Generate prediction accuracy
                actual = df['close'].tail(test_len).values
                result_1 = []
                result_2 = []
                for i in range(1, len(final_prediction)):
                    # Compare prediction to previous close price
                    if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                        result_1.append(1)
                    elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                        result_1.append(1)
                    else:
                        result_1.append(0)

                    # Compare prediction to previous prediction
                    if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                        result_2.append(1)
                    elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                        result_2.append(1)
                    else:
                        result_2.append(0)

                accuracy_1 = np.mean(result_1)
                accuracy_2 = np.mean(result_2)

                simulation8[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                              'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                  'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                              'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                  'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                              'rmse': rmse_ftr, 'mae' : mae_ftr},
                                  'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                            'rmse': rmse, 'mae': mae },
                                  'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

                # save simulation data here as checkpoint
                with open('simulation8_data.json', 'w') as fp:
                    json.dump(simulation8, fp)

                for ma in simulation8.keys():
                    print('\n' + ma)
                    print('Prediction vs Close:\t\t' + str(round(100*simulation8[ma]['accuracy']['prediction vs close'], 2))
                          + '% Accuracy')
                    print('Prediction vs Prediction:\t' + str(round(100*simulation8[ma]['accuracy']['prediction vs prediction'], 2))
                          + '% Accuracy')
                    print('MSE:\t', simulation8[ma]['final']['mse'],
                          '\nRMSE:\t', simulation8[ma]['final']['rmse'],
                          '\nMAPE:\t', simulation8[ma]['final']['mae'])#,
                          # '\nMAPE:\t', simulation[ma]['final']['mape'])
              # else:
              #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-14771.778, Time=11.98 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14135.387, Time=5.95 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15280.870, Time=10.09 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15393.475, Time=8.27 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-14981.217, Time=4.96 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14516.868, Time=13.65 sec
 ARIMA(0,3,1)(0,0,0)[0] intercept   : AIC=-15663.967, Time=10.14 sec
 ARIMA(0,3,0)(0,0,0)[0] intercept   : AIC=-13838.679, Time=5.14 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=-14734.479, Time=6.22 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-14866.409, Time=8.20 sec
 ARIMA(1,3,0)(0,0,0)[0] intercept   : AIC=-16157.403, Time=13.60 sec
 ARIMA(2,3,0)(0,0,0)[0] intercept   : AIC=-14855.623, Time=10.63 sec
 ARIMA(2,3,1)(0,0,0)[0] intercept   : AIC=-14720.644, Time=11.20 sec

Best model:  ARIMA(1,3,0)(0,0,0)[0] intercept
Total fit time: 120.058 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 0)   Log Likelihood                8103.701
Date:                Sun, 12 Dec 2021   AIC                         -16157.403
Time:                        19:41:55   BIC                         -16040.132
Sample:                             0   HQIC                        -16112.366
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
intercept  -2.802e-06   7.54e-07     -3.714      0.000   -4.28e-06   -1.32e-06
x1         -2.598e-05      0.001     -0.041      0.967      -0.001       0.001
x2         -2.599e-05      0.001     -0.047      0.963      -0.001       0.001
x3         -2.615e-05      0.001     -0.038      0.970      -0.001       0.001
x4             1.0000      0.001   1507.083      0.000       0.999       1.001
x5         -2.485e-05      0.001     -0.038      0.970      -0.001       0.001
x6         -2.807e-05   3.32e-05     -0.845      0.398   -9.32e-05    3.71e-05
x7         -2.593e-05   8.29e-05     -0.313      0.755      -0.000       0.000
x8             0.0019   7.15e-05     26.753      0.000       0.002       0.002
x9         -1.867e-06      0.001     -0.003      0.998      -0.001       0.001
x10            0.0003      0.000      0.644      0.520      -0.001       0.001
x11           -0.0025   8.93e-05    -28.145      0.000      -0.003      -0.002
x12            0.0015   8.06e-05     18.290      0.000       0.001       0.002
x13         -2.61e-05      0.000     -0.076      0.939      -0.001       0.001
x14        -7.719e-05      0.000     -0.374      0.708      -0.000       0.000
x15        -2.829e-05   8.57e-05     -0.330      0.741      -0.000       0.000
x16        -2.424e-05      0.000     -0.142      0.887      -0.000       0.000
x17        -2.292e-05   9.81e-05     -0.234      0.815      -0.000       0.000
x18         -4.39e-05      0.000     -0.429      0.668      -0.000       0.000
x19        -3.005e-05      0.000     -0.293      0.770      -0.000       0.000
x20         4.559e-05   9.36e-05      0.487      0.626      -0.000       0.000
x21        -7.981e-10      0.001  -9.88e-07      1.000      -0.002       0.002
x22        -1.557e-08      0.000     -0.000      1.000      -0.000       0.000
ar.L1         -0.6667   6.95e-05  -9587.073      0.000      -0.667      -0.667
sigma2      1.314e-10    7.8e-11      1.686      0.092   -2.14e-11    2.84e-10
===================================================================================
Ljung-Box (L1) (Q):                  90.59   Jarque-Bera (JB):           3138023.60
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.03   Skew:                             5.01
Prob(H) (two-sided):                  0.00   Kurtosis:                       308.71
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.36e+19. Standard errors may be unstable.
ARIMA order: (1, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05343, saving model to LSTM8.h5
48/48 - 3s - loss: 1.4281 - val_loss: 0.0534 - lr: 0.0010 - 3s/epoch - 68ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.3562 - val_loss: 0.0544 - lr: 0.0010 - 218ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.2612 - val_loss: 0.0554 - lr: 0.0010 - 212ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.1724 - val_loss: 0.0575 - lr: 0.0010 - 214ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.0993 - val_loss: 0.0612 - lr: 0.0010 - 221ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.0431 - val_loss: 0.0654 - lr: 0.0010 - 238ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.0138 - val_loss: 0.0658 - lr: 1.0000e-04 - 233ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.0096 - val_loss: 0.0662 - lr: 1.0000e-04 - 217ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.0054 - val_loss: 0.0667 - lr: 1.0000e-04 - 218ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05343
48/48 - 0s - loss: 1.0014 - val_loss: 0.0672 - lr: 1.0000e-04 - 230ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9973 - val_loss: 0.0676 - lr: 1.0000e-04 - 242ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9949 - val_loss: 0.0677 - lr: 1.0000e-05 - 212ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9945 - val_loss: 0.0677 - lr: 1.0000e-05 - 216ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9941 - val_loss: 0.0678 - lr: 1.0000e-05 - 223ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9937 - val_loss: 0.0678 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9933 - val_loss: 0.0679 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9929 - val_loss: 0.0679 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9925 - val_loss: 0.0680 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9921 - val_loss: 0.0680 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9917 - val_loss: 0.0681 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9913 - val_loss: 0.0681 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9909 - val_loss: 0.0682 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9904 - val_loss: 0.0682 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9900 - val_loss: 0.0683 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9896 - val_loss: 0.0684 - lr: 1.0000e-05 - 223ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9892 - val_loss: 0.0684 - lr: 1.0000e-05 - 214ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9888 - val_loss: 0.0685 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9884 - val_loss: 0.0685 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9880 - val_loss: 0.0686 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9876 - val_loss: 0.0686 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9872 - val_loss: 0.0687 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9868 - val_loss: 0.0688 - lr: 1.0000e-05 - 231ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9864 - val_loss: 0.0688 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9860 - val_loss: 0.0689 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9856 - val_loss: 0.0689 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9852 - val_loss: 0.0690 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9848 - val_loss: 0.0690 - lr: 1.0000e-05 - 241ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9844 - val_loss: 0.0691 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9840 - val_loss: 0.0692 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9836 - val_loss: 0.0692 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9832 - val_loss: 0.0693 - lr: 1.0000e-05 - 241ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9828 - val_loss: 0.0693 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9824 - val_loss: 0.0694 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9820 - val_loss: 0.0695 - lr: 1.0000e-05 - 216ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9816 - val_loss: 0.0695 - lr: 1.0000e-05 - 243ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9812 - val_loss: 0.0696 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9808 - val_loss: 0.0696 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9803 - val_loss: 0.0697 - lr: 1.0000e-05 - 212ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9799 - val_loss: 0.0698 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9795 - val_loss: 0.0698 - lr: 1.0000e-05 - 223ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05343
48/48 - 0s - loss: 0.9791 - val_loss: 0.0699 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 24.12057947793772 
RMSE:	 4.911270658183859 
MAPE:	 3.8711068958774497
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.831, Time=2.39 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.29 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16288.946, Time=7.13 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=6.21 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16226.419, Time=11.44 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-13742.844, Time=8.55 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16101.256, Time=19.59 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17006.489, Time=2.86 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17002.686, Time=2.96 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17086.654, Time=6.14 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=-16097.512, Time=15.65 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17002.132, Time=3.66 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-17004.011, Time=3.85 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 94.752 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8570.327
Date:                Sun, 12 Dec 2021   AIC                         -17086.654
Time:                        19:44:27   BIC                         -16960.001
Sample:                             0   HQIC                        -17038.014
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -2.333e-10   9.31e-21  -2.51e+10      0.000   -2.33e-10   -2.33e-10
x2         -2.326e-10   9.29e-21   -2.5e+10      0.000   -2.33e-10   -2.33e-10
x3         -2.342e-10   9.32e-21  -2.51e+10      0.000   -2.34e-10   -2.34e-10
x4             1.0000   9.31e-21   1.07e+20      0.000       1.000       1.000
x5         -2.121e-10   8.87e-21  -2.39e+10      0.000   -2.12e-10   -2.12e-10
x6         -8.055e-10   1.64e-20   -4.9e+10      0.000   -8.05e-10   -8.05e-10
x7         -2.312e-10   9.27e-21  -2.49e+10      0.000   -2.31e-10   -2.31e-10
x8          -2.26e-10   9.17e-21  -2.47e+10      0.000   -2.26e-10   -2.26e-10
x9         -1.174e-11   1.86e-21   -6.3e+09      0.000   -1.17e-11   -1.17e-11
x10        -4.486e-11   3.98e-21  -1.13e+10      0.000   -4.49e-11   -4.49e-11
x11        -2.235e-10   9.11e-21  -2.45e+10      0.000   -2.23e-10   -2.23e-10
x12         -2.28e-10   9.21e-21  -2.48e+10      0.000   -2.28e-10   -2.28e-10
x13        -2.332e-10   9.31e-21  -2.51e+10      0.000   -2.33e-10   -2.33e-10
x14         -1.78e-09   2.57e-20  -6.92e+10      0.000   -1.78e-09   -1.78e-09
x15        -2.118e-10   8.84e-21   -2.4e+10      0.000   -2.12e-10   -2.12e-10
x16         -5.28e-10    1.4e-20  -3.76e+10      0.000   -5.28e-10   -5.28e-10
x17        -2.173e-10   8.94e-21  -2.43e+10      0.000   -2.17e-10   -2.17e-10
x18         -3.83e-11   3.74e-21  -1.02e+10      0.000   -3.83e-11   -3.83e-11
x19        -2.606e-10   9.86e-21  -2.64e+10      0.000   -2.61e-10   -2.61e-10
x20        -2.433e-10   9.48e-21  -2.57e+10      0.000   -2.43e-10   -2.43e-10
x21        -3.774e-13   1.42e-24  -2.65e+11      0.000   -3.77e-13   -3.77e-13
x22        -1.096e-11   1.35e-24  -8.11e+12      0.000    -1.1e-11    -1.1e-11
ar.L1         -0.4919    1.5e-22  -3.27e+21      0.000      -0.492      -0.492
ar.L2         -0.1922   8.41e-23  -2.28e+21      0.000      -0.192      -0.192
ar.L3         -0.0462   4.01e-23  -1.15e+21      0.000      -0.046      -0.046
ma.L1         -0.7070   3.34e-22  -2.12e+21      0.000      -0.707      -0.707
sigma2      8.977e-11   6.95e-11      1.291      0.197   -4.65e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  54.80   Jarque-Bera (JB):           4212163.49
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.43
Prob(H) (two-sided):                  0.00   Kurtosis:                       357.21
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 1.65e+43. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04985, saving model to LSTM8.h5
16/16 - 4s - loss: 1.4011 - val_loss: 0.0499 - lr: 0.0010 - 4s/epoch - 245ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.3618 - val_loss: 0.0509 - lr: 0.0010 - 84ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.3261 - val_loss: 0.0519 - lr: 0.0010 - 90ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2938 - val_loss: 0.0529 - lr: 0.0010 - 99ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2643 - val_loss: 0.0541 - lr: 0.0010 - 102ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2368 - val_loss: 0.0554 - lr: 0.0010 - 99ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2195 - val_loss: 0.0555 - lr: 1.0000e-04 - 103ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2169 - val_loss: 0.0557 - lr: 1.0000e-04 - 95ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2144 - val_loss: 0.0558 - lr: 1.0000e-04 - 86ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2118 - val_loss: 0.0560 - lr: 1.0000e-04 - 89ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2093 - val_loss: 0.0561 - lr: 1.0000e-04 - 91ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2076 - val_loss: 0.0561 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2074 - val_loss: 0.0562 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2071 - val_loss: 0.0562 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2068 - val_loss: 0.0562 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2066 - val_loss: 0.0562 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2063 - val_loss: 0.0562 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2061 - val_loss: 0.0562 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2058 - val_loss: 0.0563 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2056 - val_loss: 0.0563 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2053 - val_loss: 0.0563 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2050 - val_loss: 0.0563 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2048 - val_loss: 0.0563 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2045 - val_loss: 0.0563 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2043 - val_loss: 0.0563 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2040 - val_loss: 0.0564 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2038 - val_loss: 0.0564 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2035 - val_loss: 0.0564 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2032 - val_loss: 0.0564 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2030 - val_loss: 0.0564 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2027 - val_loss: 0.0564 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2025 - val_loss: 0.0565 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2022 - val_loss: 0.0565 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2019 - val_loss: 0.0565 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2017 - val_loss: 0.0565 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2014 - val_loss: 0.0565 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2012 - val_loss: 0.0565 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2009 - val_loss: 0.0565 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2006 - val_loss: 0.0566 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2004 - val_loss: 0.0566 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.2001 - val_loss: 0.0566 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1998 - val_loss: 0.0566 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1996 - val_loss: 0.0566 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1993 - val_loss: 0.0566 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1991 - val_loss: 0.0566 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1988 - val_loss: 0.0567 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1985 - val_loss: 0.0567 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1983 - val_loss: 0.0567 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1980 - val_loss: 0.0567 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1978 - val_loss: 0.0567 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04985
16/16 - 0s - loss: 1.1975 - val_loss: 0.0567 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 24.12057947793772 
RMSE:	 4.911270658183859 
MAPE:	 3.8711068958774497

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.227409389726965 
RMSE:	 6.018920948951479 
MAPE:	 4.70810831106621
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16080.357, Time=11.09 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14973.799, Time=6.43 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15549.629, Time=1.91 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15317.999, Time=8.51 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16061.924, Time=9.72 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15376.406, Time=14.43 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16186.215, Time=3.58 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-15308.706, Time=14.04 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-14920.393, Time=15.30 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-16184.203, Time=3.42 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 88.460 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8118.107
Date:                Sun, 12 Dec 2021   AIC                         -16186.215
Time:                        19:53:57   BIC                         -16068.944
Sample:                             0   HQIC                        -16141.178
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -9.919e-15      0.000   -8.4e-11      1.000      -0.000       0.000
x2          3.194e-15    6.3e-05   5.07e-11      1.000      -0.000       0.000
x3          3.066e-15   7.71e-05   3.98e-11      1.000      -0.000       0.000
x4             1.0000    4.4e-05   2.27e+04      0.000       1.000       1.000
x5         -3.977e-15   4.68e-05  -8.49e-11      1.000   -9.18e-05    9.18e-05
x6         -5.906e-17   8.34e-05  -7.08e-13      1.000      -0.000       0.000
x7         -8.726e-15   7.85e-05  -1.11e-10      1.000      -0.000       0.000
x8             0.0014   4.94e-05     27.704      0.000       0.001       0.001
x9         -3.542e-15      0.001  -2.63e-12      1.000      -0.003       0.003
x10           -0.0012      0.001     -1.566      0.117      -0.003       0.000
x11            0.0052   3.01e-05    172.396      0.000       0.005       0.005
x12           -0.0065      0.000    -49.747      0.000      -0.007      -0.006
x13         1.963e-14   7.85e-05    2.5e-10      1.000      -0.000       0.000
x14        -2.134e-14      0.000  -1.01e-10      1.000      -0.000       0.000
x15         3.464e-12      0.000   2.92e-08      1.000      -0.000       0.000
x16        -7.174e-13   6.45e-05  -1.11e-08      1.000      -0.000       0.000
x17         2.537e-13   7.42e-05   3.42e-09      1.000      -0.000       0.000
x18        -2.964e-15      0.000  -7.78e-12      1.000      -0.001       0.001
x19        -3.613e-12   8.67e-05  -4.17e-08      1.000      -0.000       0.000
x20         6.244e-14      0.000    2.1e-10      1.000      -0.001       0.001
x21        -4.242e-16      0.000  -1.47e-12      1.000      -0.001       0.001
x22        -2.128e-15      0.001  -1.74e-12      1.000      -0.002       0.002
ma.L1         -1.3894   4.16e-05  -3.34e+04      0.000      -1.389      -1.389
ma.L2          0.4036      0.000   3637.465      0.000       0.403       0.404
sigma2      1.287e-10   7.27e-11      1.770      0.077   -1.38e-11    2.71e-10
===================================================================================
Ljung-Box (L1) (Q):                  69.00   Jarque-Bera (JB):           6269147.49
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            12.07
Prob(H) (two-sided):                  0.00   Kurtosis:                       434.65
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 6.47e+20. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04774, saving model to LSTM8.h5
17/17 - 4s - loss: 1.4119 - val_loss: 0.0477 - lr: 0.0010 - 4s/epoch - 223ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.3900 - val_loss: 0.0486 - lr: 0.0010 - 91ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.3678 - val_loss: 0.0495 - lr: 0.0010 - 87ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.3442 - val_loss: 0.0506 - lr: 0.0010 - 91ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.3196 - val_loss: 0.0517 - lr: 0.0010 - 89ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2946 - val_loss: 0.0530 - lr: 0.0010 - 96ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2783 - val_loss: 0.0531 - lr: 1.0000e-04 - 93ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2759 - val_loss: 0.0532 - lr: 1.0000e-04 - 101ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2735 - val_loss: 0.0534 - lr: 1.0000e-04 - 99ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2712 - val_loss: 0.0535 - lr: 1.0000e-04 - 91ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2688 - val_loss: 0.0536 - lr: 1.0000e-04 - 93ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2673 - val_loss: 0.0536 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2671 - val_loss: 0.0536 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2669 - val_loss: 0.0537 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2667 - val_loss: 0.0537 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2664 - val_loss: 0.0537 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2662 - val_loss: 0.0537 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2660 - val_loss: 0.0537 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2658 - val_loss: 0.0537 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2655 - val_loss: 0.0537 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2653 - val_loss: 0.0537 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2651 - val_loss: 0.0538 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2649 - val_loss: 0.0538 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2646 - val_loss: 0.0538 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2644 - val_loss: 0.0538 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2642 - val_loss: 0.0538 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2640 - val_loss: 0.0538 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2637 - val_loss: 0.0538 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2635 - val_loss: 0.0539 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2633 - val_loss: 0.0539 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2631 - val_loss: 0.0539 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2629 - val_loss: 0.0539 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2626 - val_loss: 0.0539 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2624 - val_loss: 0.0539 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2622 - val_loss: 0.0539 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2620 - val_loss: 0.0540 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2617 - val_loss: 0.0540 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2615 - val_loss: 0.0540 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2613 - val_loss: 0.0540 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2611 - val_loss: 0.0540 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2609 - val_loss: 0.0540 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2606 - val_loss: 0.0541 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2604 - val_loss: 0.0541 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2602 - val_loss: 0.0541 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2600 - val_loss: 0.0541 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2598 - val_loss: 0.0541 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2595 - val_loss: 0.0541 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2593 - val_loss: 0.0541 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2591 - val_loss: 0.0542 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2589 - val_loss: 0.0542 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04774
17/17 - 0s - loss: 1.2586 - val_loss: 0.0542 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 24.12057947793772 
RMSE:	 4.911270658183859 
MAPE:	 3.8711068958774497

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.227409389726965 
RMSE:	 6.018920948951479 
MAPE:	 4.70810831106621

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 47.6040579193988 
RMSE:	 6.8995694010132835 
MAPE:	 5.522605601178568
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.780, Time=2.79 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.30 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15584.877, Time=8.35 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=5.71 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15271.475, Time=7.68 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15128.422, Time=9.97 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16352.675, Time=17.53 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17028.022, Time=4.81 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17002.621, Time=3.21 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17085.445, Time=6.37 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=17.03 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17001.997, Time=3.96 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16996.668, Time=4.14 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 95.868 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.723
Date:                Sun, 12 Dec 2021   AIC                         -17085.445
Time:                        19:59:36   BIC                         -16958.792
Sample:                             0   HQIC                        -17036.805
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1           -2.8e-10   1.36e-20  -2.05e+10      0.000    -2.8e-10    -2.8e-10
x2         -2.817e-10   1.37e-20  -2.06e+10      0.000   -2.82e-10   -2.82e-10
x3         -2.805e-10   1.36e-20  -2.06e+10      0.000    -2.8e-10    -2.8e-10
x4             1.0000   1.37e-20   7.33e+19      0.000       1.000       1.000
x5         -2.598e-10   1.31e-20  -1.98e+10      0.000    -2.6e-10    -2.6e-10
x6         -1.389e-09   2.98e-20  -4.66e+10      0.000   -1.39e-09   -1.39e-09
x7         -2.789e-10   1.36e-20  -2.05e+10      0.000   -2.79e-10   -2.79e-10
x8         -2.761e-10   1.35e-20  -2.04e+10      0.000   -2.76e-10   -2.76e-10
x9         -2.219e-12   3.36e-22   -6.6e+09      0.000   -2.22e-12   -2.22e-12
x10        -1.345e-10   9.37e-21  -1.43e+10      0.000   -1.34e-10   -1.34e-10
x11        -2.899e-10   1.39e-20  -2.09e+10      0.000    -2.9e-10    -2.9e-10
x12        -2.602e-10   1.32e-20  -1.98e+10      0.000    -2.6e-10    -2.6e-10
x13        -2.807e-10   1.36e-20  -2.06e+10      0.000   -2.81e-10   -2.81e-10
x14         -1.87e-09   3.52e-20  -5.31e+10      0.000   -1.87e-09   -1.87e-09
x15        -2.825e-10   1.37e-20  -2.07e+10      0.000   -2.82e-10   -2.82e-10
x16        -8.187e-11   7.33e-21  -1.12e+10      0.000   -8.19e-11   -8.19e-11
x17        -2.441e-10   1.27e-20  -1.92e+10      0.000   -2.44e-10   -2.44e-10
x18        -6.411e-10   2.06e-20  -3.11e+10      0.000   -6.41e-10   -6.41e-10
x19        -2.929e-10   1.39e-20  -2.11e+10      0.000   -2.93e-10   -2.93e-10
x20        -4.339e-10    1.7e-20  -2.56e+10      0.000   -4.34e-10   -4.34e-10
x21        -3.589e-13   2.52e-24  -1.42e+11      0.000   -3.59e-13   -3.59e-13
x22        -1.088e-11   2.36e-24   -4.6e+12      0.000   -1.09e-11   -1.09e-11
ar.L1         -0.4923   1.46e-22  -3.37e+21      0.000      -0.492      -0.492
ar.L2         -0.1923   8.47e-23  -2.27e+21      0.000      -0.192      -0.192
ar.L3         -0.0462   4.02e-23  -1.15e+21      0.000      -0.046      -0.046
ma.L1         -0.7077   3.31e-22  -2.14e+21      0.000      -0.708      -0.708
sigma2       8.99e-11   6.95e-11      1.293      0.196   -4.64e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  55.15   Jarque-Bera (JB):           4171184.78
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.27
Prob(H) (two-sided):                  0.00   Kurtosis:                       355.49
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.53e+42. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04236, saving model to LSTM8.h5
10/10 - 4s - loss: 1.4274 - val_loss: 0.0424 - lr: 0.0010 - 4s/epoch - 357ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.3956 - val_loss: 0.0430 - lr: 0.0010 - 62ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.3644 - val_loss: 0.0438 - lr: 0.0010 - 60ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.3323 - val_loss: 0.0445 - lr: 0.0010 - 61ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2994 - val_loss: 0.0453 - lr: 0.0010 - 67ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2661 - val_loss: 0.0462 - lr: 0.0010 - 63ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2424 - val_loss: 0.0463 - lr: 1.0000e-04 - 62ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2392 - val_loss: 0.0464 - lr: 1.0000e-04 - 61ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2360 - val_loss: 0.0465 - lr: 1.0000e-04 - 71ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2329 - val_loss: 0.0465 - lr: 1.0000e-04 - 74ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2298 - val_loss: 0.0466 - lr: 1.0000e-04 - 71ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2277 - val_loss: 0.0466 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2274 - val_loss: 0.0467 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2271 - val_loss: 0.0467 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2268 - val_loss: 0.0467 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2265 - val_loss: 0.0467 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2262 - val_loss: 0.0467 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2259 - val_loss: 0.0467 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2256 - val_loss: 0.0467 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2253 - val_loss: 0.0467 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2250 - val_loss: 0.0467 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2247 - val_loss: 0.0467 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2244 - val_loss: 0.0467 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2241 - val_loss: 0.0468 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2238 - val_loss: 0.0468 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2235 - val_loss: 0.0468 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2232 - val_loss: 0.0468 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2229 - val_loss: 0.0468 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2226 - val_loss: 0.0468 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2223 - val_loss: 0.0468 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2220 - val_loss: 0.0468 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2217 - val_loss: 0.0468 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2215 - val_loss: 0.0468 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2212 - val_loss: 0.0468 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2209 - val_loss: 0.0469 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2206 - val_loss: 0.0469 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2203 - val_loss: 0.0469 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2200 - val_loss: 0.0469 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2197 - val_loss: 0.0469 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2194 - val_loss: 0.0469 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2191 - val_loss: 0.0469 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2188 - val_loss: 0.0469 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2185 - val_loss: 0.0469 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2183 - val_loss: 0.0469 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2180 - val_loss: 0.0469 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2177 - val_loss: 0.0470 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2174 - val_loss: 0.0470 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2171 - val_loss: 0.0470 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2168 - val_loss: 0.0470 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2165 - val_loss: 0.0470 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04236
10/10 - 0s - loss: 1.2162 - val_loss: 0.0470 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 24.12057947793772 
RMSE:	 4.911270658183859 
MAPE:	 3.8711068958774497

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.227409389726965 
RMSE:	 6.018920948951479 
MAPE:	 4.70810831106621

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 47.6040579193988 
RMSE:	 6.8995694010132835 
MAPE:	 5.522605601178568

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 155.67335739769726 
RMSE:	 12.476912975479843 
MAPE:	 11.236116903479964
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17059.325, Time=4.12 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.593, Time=4.50 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16133.019, Time=6.20 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.593, Time=6.06 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16091.980, Time=7.55 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16009.844, Time=12.63 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-15757.180, Time=9.74 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17029.439, Time=4.68 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-17000.917, Time=4.00 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=45.027, Time=4.74 sec

Best model:  ARIMA(1,3,1)(0,0,0)[0]          
Total fit time: 64.246 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 1)   Log Likelihood                8554.662
Date:                Sun, 12 Dec 2021   AIC                         -17059.325
Time:                        20:08:53   BIC                         -16942.054
Sample:                             0   HQIC                        -17014.288
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -1.409e-10   5.52e-21  -2.55e+10      0.000   -1.41e-10   -1.41e-10
x2         -1.378e-10   5.47e-21  -2.52e+10      0.000   -1.38e-10   -1.38e-10
x3         -1.323e-10   5.35e-21  -2.47e+10      0.000   -1.32e-10   -1.32e-10
x4             1.0000   5.41e-21   1.85e+20      0.000       1.000       1.000
x5         -1.221e-10   5.15e-21  -2.37e+10      0.000   -1.22e-10   -1.22e-10
x6         -8.465e-10    1.3e-20  -6.53e+10      0.000   -8.47e-10   -8.47e-10
x7           -1.3e-10   5.32e-21  -2.44e+10      0.000    -1.3e-10    -1.3e-10
x8         -1.267e-10   5.27e-21  -2.41e+10      0.000   -1.27e-10   -1.27e-10
x9         -2.032e-11   6.67e-22  -3.05e+10      0.000   -2.03e-11   -2.03e-11
x10        -5.319e-11    2.3e-21  -2.31e+10      0.000   -5.32e-11   -5.32e-11
x11        -1.275e-10   5.28e-21  -2.42e+10      0.000   -1.28e-10   -1.28e-10
x12        -1.262e-10   5.23e-21  -2.41e+10      0.000   -1.26e-10   -1.26e-10
x13        -1.339e-10   5.39e-21  -2.49e+10      0.000   -1.34e-10   -1.34e-10
x14        -1.092e-09   1.55e-20  -7.06e+10      0.000   -1.09e-09   -1.09e-09
x15        -1.342e-10   5.42e-21  -2.48e+10      0.000   -1.34e-10   -1.34e-10
x16         -2.01e-10   6.63e-21  -3.03e+10      0.000   -2.01e-10   -2.01e-10
x17        -1.144e-10   5.01e-21  -2.29e+10      0.000   -1.14e-10   -1.14e-10
x18        -9.245e-11   4.49e-21  -2.06e+10      0.000   -9.24e-11   -9.24e-11
x19        -1.646e-10   6.01e-21  -2.74e+10      0.000   -1.65e-10   -1.65e-10
x20        -2.482e-10   7.35e-21  -3.37e+10      0.000   -2.48e-10   -2.48e-10
x21        -3.385e-12   3.14e-24  -1.08e+12      0.000   -3.39e-12   -3.39e-12
x22        -8.066e-11   2.47e-23  -3.26e+12      0.000   -8.07e-11   -8.07e-11
ar.L1         -0.2877   2.48e-22  -1.16e+21      0.000      -0.288      -0.288
ma.L1         -0.9134   1.05e-21   -8.7e+20      0.000      -0.913      -0.913
sigma2      9.332e-11   6.96e-11      1.340      0.180   -4.32e-11     2.3e-10
===================================================================================
Ljung-Box (L1) (Q):                  84.37   Jarque-Bera (JB):           4308764.36
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             5.22
Prob(H) (two-sided):                  0.00   Kurtosis:                       361.26
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.32e+42. Standard errors may be unstable.
ARIMA order: (1, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05262, saving model to LSTM8.h5
45/45 - 4s - loss: 1.4483 - val_loss: 0.0526 - lr: 0.0010 - 4s/epoch - 79ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.3960 - val_loss: 0.0542 - lr: 0.0010 - 216ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.3557 - val_loss: 0.0557 - lr: 0.0010 - 212ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.3084 - val_loss: 0.0584 - lr: 0.0010 - 211ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.2412 - val_loss: 0.0628 - lr: 0.0010 - 220ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.1638 - val_loss: 0.0689 - lr: 0.0010 - 211ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.1185 - val_loss: 0.0696 - lr: 1.0000e-04 - 217ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.1122 - val_loss: 0.0703 - lr: 1.0000e-04 - 221ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.1062 - val_loss: 0.0710 - lr: 1.0000e-04 - 219ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.1005 - val_loss: 0.0718 - lr: 1.0000e-04 - 214ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0948 - val_loss: 0.0725 - lr: 1.0000e-04 - 214ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0913 - val_loss: 0.0726 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0907 - val_loss: 0.0727 - lr: 1.0000e-05 - 213ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0902 - val_loss: 0.0727 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0896 - val_loss: 0.0728 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0891 - val_loss: 0.0729 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0885 - val_loss: 0.0730 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0880 - val_loss: 0.0730 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0874 - val_loss: 0.0731 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0869 - val_loss: 0.0732 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0863 - val_loss: 0.0733 - lr: 1.0000e-05 - 215ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0858 - val_loss: 0.0734 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0852 - val_loss: 0.0734 - lr: 1.0000e-05 - 216ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0847 - val_loss: 0.0735 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0841 - val_loss: 0.0736 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0836 - val_loss: 0.0737 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0830 - val_loss: 0.0738 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0824 - val_loss: 0.0739 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0819 - val_loss: 0.0739 - lr: 1.0000e-05 - 215ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0813 - val_loss: 0.0740 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0808 - val_loss: 0.0741 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0802 - val_loss: 0.0742 - lr: 1.0000e-05 - 213ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0797 - val_loss: 0.0743 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0791 - val_loss: 0.0744 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0785 - val_loss: 0.0744 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0780 - val_loss: 0.0745 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0774 - val_loss: 0.0746 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0769 - val_loss: 0.0747 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0763 - val_loss: 0.0748 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0757 - val_loss: 0.0749 - lr: 1.0000e-05 - 209ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0752 - val_loss: 0.0750 - lr: 1.0000e-05 - 207ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0746 - val_loss: 0.0750 - lr: 1.0000e-05 - 207ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0740 - val_loss: 0.0751 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0735 - val_loss: 0.0752 - lr: 1.0000e-05 - 207ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0729 - val_loss: 0.0753 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0723 - val_loss: 0.0754 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0718 - val_loss: 0.0755 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0712 - val_loss: 0.0755 - lr: 1.0000e-05 - 213ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0706 - val_loss: 0.0756 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0701 - val_loss: 0.0757 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05262
45/45 - 0s - loss: 1.0695 - val_loss: 0.0758 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 24.12057947793772 
RMSE:	 4.911270658183859 
MAPE:	 3.8711068958774497

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.227409389726965 
RMSE:	 6.018920948951479 
MAPE:	 4.70810831106621

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 47.6040579193988 
RMSE:	 6.8995694010132835 
MAPE:	 5.522605601178568

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 155.67335739769726 
RMSE:	 12.476912975479843 
MAPE:	 11.236116903479964

KAMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 19.84916238053282 
RMSE:	 4.45523987912355 
MAPE:	 3.572304554405335
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-17003.733, Time=2.57 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14572.592, Time=4.14 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15587.551, Time=7.50 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14570.592, Time=5.87 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16365.334, Time=9.84 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16163.760, Time=13.20 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16245.181, Time=13.32 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17028.017, Time=4.78 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-17106.133, Time=5.54 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17085.425, Time=6.93 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=-17000.553, Time=3.98 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 77.702 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood                8579.066
Date:                Sun, 12 Dec 2021   AIC                         -17106.133
Time:                        20:13:15   BIC                         -16984.171
Sample:                             0   HQIC                        -17059.294
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -3.048e-10   1.69e-20   -1.8e+10      0.000   -3.05e-10   -3.05e-10
x2         -3.042e-10   1.75e-20  -1.74e+10      0.000   -3.04e-10   -3.04e-10
x3         -3.108e-10   1.62e-20  -1.92e+10      0.000   -3.11e-10   -3.11e-10
x4             1.0000   1.69e-20   5.91e+19      0.000       1.000       1.000
x5         -2.767e-10   1.61e-20  -1.72e+10      0.000   -2.77e-10   -2.77e-10
x6         -6.072e-09   1.38e-19  -4.42e+10      0.000   -6.07e-09   -6.07e-09
x7           -2.8e-10   1.62e-20  -1.73e+10      0.000    -2.8e-10    -2.8e-10
x8         -2.792e-10   1.65e-20  -1.69e+10      0.000   -2.79e-10   -2.79e-10
x9         -1.502e-10   1.02e-21  -1.48e+11      0.000    -1.5e-10    -1.5e-10
x10        -2.482e-10    4.3e-21  -5.77e+10      0.000   -2.48e-10   -2.48e-10
x11        -2.764e-10   1.64e-20  -1.69e+10      0.000   -2.76e-10   -2.76e-10
x12        -2.857e-10   1.64e-20  -1.74e+10      0.000   -2.86e-10   -2.86e-10
x13        -2.944e-10   1.66e-20  -1.77e+10      0.000   -2.94e-10   -2.94e-10
x14        -2.403e-09   4.86e-20  -4.95e+10      0.000    -2.4e-09    -2.4e-09
x15        -3.368e-10   1.81e-20  -1.86e+10      0.000   -3.37e-10   -3.37e-10
x16        -2.169e-10   1.45e-20  -1.49e+10      0.000   -2.17e-10   -2.17e-10
x17        -2.124e-10   1.44e-20  -1.47e+10      0.000   -2.12e-10   -2.12e-10
x18        -9.125e-10   2.98e-20  -3.06e+10      0.000   -9.13e-10   -9.13e-10
x19        -3.698e-10    1.9e-20  -1.95e+10      0.000    -3.7e-10    -3.7e-10
x20          -8.9e-10   2.94e-20  -3.03e+10      0.000    -8.9e-10    -8.9e-10
x21        -1.844e-11   1.86e-22   -9.9e+10      0.000   -1.84e-11   -1.84e-11
x22        -2.169e-10   5.04e-22   -4.3e+11      0.000   -2.17e-10   -2.17e-10
ar.L1         -1.2011    7.4e-23  -1.62e+22      0.000      -1.201      -1.201
ar.L2         -0.9017   1.51e-22  -5.98e+21      0.000      -0.902      -0.902
ar.L3         -0.4014   9.48e-23  -4.23e+21      0.000      -0.401      -0.401
sigma2      8.782e-11   6.95e-11      1.264      0.206   -4.84e-11    2.24e-10
===================================================================================
Ljung-Box (L1) (Q):                   3.61   Jarque-Bera (JB):             16191.93
Prob(Q):                              0.06   Prob(JB):                         0.00
Heteroskedasticity (H):               0.35   Skew:                             0.59
Prob(H) (two-sided):                  0.00   Kurtosis:                        24.94
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 3.23e+40. Standard errors may be unstable.
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04423, saving model to LSTM8.h5
58/58 - 4s - loss: 1.2900 - val_loss: 0.0442 - lr: 0.0010 - 4s/epoch - 72ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04423
58/58 - 0s - loss: 1.1398 - val_loss: 0.0484 - lr: 0.0010 - 277ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04423
58/58 - 0s - loss: 1.0330 - val_loss: 0.0527 - lr: 0.0010 - 258ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.9499 - val_loss: 0.0571 - lr: 0.0010 - 270ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.8869 - val_loss: 0.0616 - lr: 0.0010 - 257ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.8390 - val_loss: 0.0662 - lr: 0.0010 - 259ms/epoch - 4ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.8147 - val_loss: 0.0666 - lr: 1.0000e-04 - 250ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.8111 - val_loss: 0.0671 - lr: 1.0000e-04 - 264ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.8075 - val_loss: 0.0676 - lr: 1.0000e-04 - 289ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.8039 - val_loss: 0.0681 - lr: 1.0000e-04 - 266ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.8004 - val_loss: 0.0687 - lr: 1.0000e-04 - 265ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7982 - val_loss: 0.0687 - lr: 1.0000e-05 - 278ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7978 - val_loss: 0.0688 - lr: 1.0000e-05 - 285ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7975 - val_loss: 0.0688 - lr: 1.0000e-05 - 292ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7971 - val_loss: 0.0689 - lr: 1.0000e-05 - 272ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7967 - val_loss: 0.0690 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7964 - val_loss: 0.0690 - lr: 1.0000e-05 - 270ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7960 - val_loss: 0.0691 - lr: 1.0000e-05 - 258ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7956 - val_loss: 0.0692 - lr: 1.0000e-05 - 269ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7952 - val_loss: 0.0692 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7948 - val_loss: 0.0693 - lr: 1.0000e-05 - 264ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7944 - val_loss: 0.0694 - lr: 1.0000e-05 - 266ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7940 - val_loss: 0.0694 - lr: 1.0000e-05 - 267ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7937 - val_loss: 0.0695 - lr: 1.0000e-05 - 256ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7933 - val_loss: 0.0696 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7929 - val_loss: 0.0697 - lr: 1.0000e-05 - 266ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7925 - val_loss: 0.0697 - lr: 1.0000e-05 - 261ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7921 - val_loss: 0.0698 - lr: 1.0000e-05 - 264ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7917 - val_loss: 0.0699 - lr: 1.0000e-05 - 260ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7912 - val_loss: 0.0700 - lr: 1.0000e-05 - 266ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7908 - val_loss: 0.0701 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7904 - val_loss: 0.0702 - lr: 1.0000e-05 - 260ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7900 - val_loss: 0.0702 - lr: 1.0000e-05 - 267ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7896 - val_loss: 0.0703 - lr: 1.0000e-05 - 266ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7892 - val_loss: 0.0704 - lr: 1.0000e-05 - 261ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7888 - val_loss: 0.0705 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7884 - val_loss: 0.0706 - lr: 1.0000e-05 - 261ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7880 - val_loss: 0.0707 - lr: 1.0000e-05 - 270ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7876 - val_loss: 0.0708 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7872 - val_loss: 0.0709 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7868 - val_loss: 0.0710 - lr: 1.0000e-05 - 268ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7864 - val_loss: 0.0711 - lr: 1.0000e-05 - 270ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7860 - val_loss: 0.0712 - lr: 1.0000e-05 - 258ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7855 - val_loss: 0.0713 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7851 - val_loss: 0.0714 - lr: 1.0000e-05 - 267ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7847 - val_loss: 0.0715 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7843 - val_loss: 0.0716 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7839 - val_loss: 0.0717 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7835 - val_loss: 0.0718 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7831 - val_loss: 0.0719 - lr: 1.0000e-05 - 261ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04423
58/58 - 0s - loss: 0.7827 - val_loss: 0.0720 - lr: 1.0000e-05 - 258ms/epoch - 4ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 24.12057947793772 
RMSE:	 4.911270658183859 
MAPE:	 3.8711068958774497

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.227409389726965 
RMSE:	 6.018920948951479 
MAPE:	 4.70810831106621

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 47.6040579193988 
RMSE:	 6.8995694010132835 
MAPE:	 5.522605601178568

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 155.67335739769726 
RMSE:	 12.476912975479843 
MAPE:	 11.236116903479964

KAMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 19.84916238053282 
RMSE:	 4.45523987912355 
MAPE:	 3.572304554405335

MIDPOINT
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 21.813261360012138 
RMSE:	 4.67046693169025 
MAPE:	 3.6223152079979295
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16954.347, Time=2.93 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14725.736, Time=2.39 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16732.390, Time=8.12 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15913.358, Time=7.01 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16550.077, Time=10.42 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15004.835, Time=9.62 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16027.273, Time=10.33 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-16934.995, Time=2.68 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16924.758, Time=3.47 sec
 ARIMA(1,3,1)(0,0,0)[0] intercept   : AIC=-16952.347, Time=2.52 sec

Best model:  ARIMA(1,3,1)(0,0,0)[0]          
Total fit time: 59.502 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(1, 3, 1)   Log Likelihood                8502.173
Date:                Sun, 12 Dec 2021   AIC                         -16954.347
Time:                        20:16:27   BIC                         -16837.076
Sample:                             0   HQIC                        -16909.310
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1          3.409e-14   2.62e-06    1.3e-08      1.000   -5.13e-06    5.13e-06
x2          1.816e-14   2.62e-06   6.93e-09      1.000   -5.13e-06    5.13e-06
x3         -2.039e-15   2.47e-06  -8.26e-10      1.000   -4.84e-06    4.84e-06
x4             1.0000    2.5e-06      4e+05      0.000       1.000       1.000
x5          2.488e-12   2.48e-06      1e-06      1.000   -4.86e-06    4.86e-06
x6           2.84e-15   6.48e-06   4.38e-10      1.000   -1.27e-05    1.27e-05
x7          3.618e-13   3.24e-06   1.12e-07      1.000   -6.36e-06    6.36e-06
x8            -0.0002   4.44e-06    -43.079      0.000      -0.000      -0.000
x9           2.93e-14    6.3e-08   4.65e-07      1.000   -1.23e-07    1.23e-07
x10        -2.843e-05   9.63e-06     -2.951      0.003   -4.73e-05   -9.55e-06
x11            0.0002   3.28e-06     53.981      0.000       0.000       0.000
x12            0.0001   5.63e-06     23.078      0.000       0.000       0.000
x13        -2.595e-14   2.63e-06  -9.88e-09      1.000   -5.15e-06    5.15e-06
x14        -6.497e-14   5.76e-06  -1.13e-08      1.000   -1.13e-05    1.13e-05
x15         1.699e-12   3.08e-06   5.51e-07      1.000   -6.04e-06    6.04e-06
x16        -3.969e-12   4.77e-06  -8.33e-07      1.000   -9.34e-06    9.34e-06
x17         5.452e-12   8.58e-07   6.35e-06      1.000   -1.68e-06    1.68e-06
x18         -3.68e-13   1.33e-05  -2.76e-08      1.000   -2.61e-05    2.61e-05
x19        -5.643e-13   4.61e-06  -1.22e-07      1.000   -9.03e-06    9.03e-06
x20         6.651e-14    4.9e-05   1.36e-09      1.000   -9.61e-05    9.61e-05
x21         -1.76e-16   8.47e-11  -2.08e-06      1.000   -1.66e-10    1.66e-10
x22         -7.82e-16   1.75e-10  -4.47e-06      1.000   -3.43e-10    3.43e-10
ar.L1         -0.2858   5.46e-08  -5.24e+06      0.000      -0.286      -0.286
ma.L1         -0.9143   5.59e-08  -1.63e+07      0.000      -0.914      -0.914
sigma2          1e-10   6.99e-11      1.430      0.153   -3.71e-11    2.37e-10
===================================================================================
Ljung-Box (L1) (Q):                  84.00   Jarque-Bera (JB):           4822228.07
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            -6.05
Prob(H) (two-sided):                  0.00   Kurtosis:                       381.97
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 3.54e+27. Standard errors may be unstable.
ARIMA order: (1, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05045, saving model to LSTM8.h5
43/43 - 4s - loss: 1.4232 - val_loss: 0.0504 - lr: 0.0010 - 4s/epoch - 92ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.3899 - val_loss: 0.0529 - lr: 0.0010 - 217ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.3362 - val_loss: 0.0554 - lr: 0.0010 - 216ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.2675 - val_loss: 0.0585 - lr: 0.0010 - 235ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.2062 - val_loss: 0.0621 - lr: 0.0010 - 194ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1541 - val_loss: 0.0659 - lr: 0.0010 - 211ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1248 - val_loss: 0.0663 - lr: 1.0000e-04 - 220ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1205 - val_loss: 0.0667 - lr: 1.0000e-04 - 204ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1162 - val_loss: 0.0671 - lr: 1.0000e-04 - 209ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1121 - val_loss: 0.0675 - lr: 1.0000e-04 - 192ms/epoch - 4ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1080 - val_loss: 0.0679 - lr: 1.0000e-04 - 209ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1054 - val_loss: 0.0680 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1050 - val_loss: 0.0680 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1046 - val_loss: 0.0681 - lr: 1.0000e-05 - 196ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1042 - val_loss: 0.0681 - lr: 1.0000e-05 - 207ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1038 - val_loss: 0.0682 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1034 - val_loss: 0.0682 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1030 - val_loss: 0.0682 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1026 - val_loss: 0.0683 - lr: 1.0000e-05 - 197ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1022 - val_loss: 0.0683 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1018 - val_loss: 0.0684 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1014 - val_loss: 0.0684 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1010 - val_loss: 0.0685 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1006 - val_loss: 0.0685 - lr: 1.0000e-05 - 199ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.1002 - val_loss: 0.0686 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0998 - val_loss: 0.0686 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0994 - val_loss: 0.0687 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0990 - val_loss: 0.0687 - lr: 1.0000e-05 - 196ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0986 - val_loss: 0.0688 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0982 - val_loss: 0.0688 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0978 - val_loss: 0.0689 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0974 - val_loss: 0.0689 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0970 - val_loss: 0.0690 - lr: 1.0000e-05 - 202ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0966 - val_loss: 0.0690 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0962 - val_loss: 0.0691 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0958 - val_loss: 0.0691 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0954 - val_loss: 0.0692 - lr: 1.0000e-05 - 199ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0950 - val_loss: 0.0692 - lr: 1.0000e-05 - 201ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0946 - val_loss: 0.0693 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0942 - val_loss: 0.0693 - lr: 1.0000e-05 - 233ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0938 - val_loss: 0.0694 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0934 - val_loss: 0.0694 - lr: 1.0000e-05 - 198ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0930 - val_loss: 0.0695 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0926 - val_loss: 0.0695 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0922 - val_loss: 0.0696 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0918 - val_loss: 0.0696 - lr: 1.0000e-05 - 197ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0914 - val_loss: 0.0697 - lr: 1.0000e-05 - 200ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0910 - val_loss: 0.0697 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0906 - val_loss: 0.0698 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0902 - val_loss: 0.0698 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05045
43/43 - 0s - loss: 1.0898 - val_loss: 0.0699 - lr: 1.0000e-05 - 201ms/epoch - 5ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 24.12057947793772 
RMSE:	 4.911270658183859 
MAPE:	 3.8711068958774497

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.227409389726965 
RMSE:	 6.018920948951479 
MAPE:	 4.70810831106621

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 47.6040579193988 
RMSE:	 6.8995694010132835 
MAPE:	 5.522605601178568

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 155.67335739769726 
RMSE:	 12.476912975479843 
MAPE:	 11.236116903479964

KAMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 19.84916238053282 
RMSE:	 4.45523987912355 
MAPE:	 3.572304554405335

MIDPOINT
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 21.813261360012138 
RMSE:	 4.67046693169025 
MAPE:	 3.6223152079979295

T3
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 67.60005597705626 
RMSE:	 8.221925320571591 
MAPE:	 6.604025072859764
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16412.930, Time=10.43 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14867.265, Time=6.40 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15902.803, Time=5.38 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-15117.003, Time=7.68 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15669.652, Time=7.77 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-12676.374, Time=9.47 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16418.724, Time=9.19 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-15107.772, Time=14.60 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15708.742, Time=15.23 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-13418.641, Time=23.92 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 110.098 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8234.362
Date:                Sun, 12 Dec 2021   AIC                         -16418.724
Time:                        20:21:29   BIC                         -16301.453
Sample:                             0   HQIC                        -16373.687
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -1.784e-07      0.001     -0.000      1.000      -0.002       0.002
x2         -1.784e-07      0.001     -0.000      1.000      -0.003       0.003
x3         -1.794e-07      0.001     -0.000      1.000      -0.002       0.002
x4             1.0000      0.000   2616.546      0.000       0.999       1.001
x5         -1.704e-07      0.000     -0.000      1.000      -0.001       0.001
x6         -2.858e-07   3.31e-05     -0.009      0.993   -6.52e-05    6.46e-05
x7         -1.754e-07      0.001     -0.000      1.000      -0.002       0.002
x8             0.0007      0.000      3.091      0.002       0.000       0.001
x9          3.313e-08      0.000   9.39e-05      1.000      -0.001       0.001
x10         3.499e-06      0.000      0.022      0.983      -0.000       0.000
x11           -0.0003      0.000     -1.284      0.199      -0.001       0.000
x12        -6.362e-05      0.000     -0.260      0.795      -0.001       0.000
x13        -1.783e-07      0.000     -0.001      0.999      -0.000       0.000
x14        -5.244e-07      0.001     -0.001      0.999      -0.001       0.001
x15        -1.737e-07      0.000     -0.001      0.999      -0.000       0.000
x16        -2.583e-07      0.000     -0.001      0.999      -0.000       0.000
x17         -1.74e-07      0.000     -0.001      0.999      -0.000       0.000
x18        -5.776e-08      0.000     -0.000      1.000      -0.000       0.000
x19         -1.95e-07      0.000     -0.002      0.999      -0.000       0.000
x20          1.72e-07      0.000      0.001      0.999      -0.000       0.000
x21        -7.548e-10      0.001  -9.93e-07      1.000      -0.001       0.001
x22        -1.194e-08      0.000  -8.47e-05      1.000      -0.000       0.000
ma.L1         -1.3862   1.58e-05  -8.78e+04      0.000      -1.386      -1.386
ma.L2          0.4019   4.28e-05   9396.834      0.000       0.402       0.402
sigma2      1.265e-10   7.58e-11      1.669      0.095    -2.2e-11    2.75e-10
===================================================================================
Ljung-Box (L1) (Q):                  66.79   Jarque-Bera (JB):           5900482.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                           -11.32
Prob(H) (two-sided):                  0.00   Kurtosis:                       421.81
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.07e+19. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05051, saving model to LSTM8.h5
90/90 - 4s - loss: 1.3468 - val_loss: 0.0505 - lr: 0.0010 - 4s/epoch - 43ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.05051
90/90 - 0s - loss: 1.1420 - val_loss: 0.0570 - lr: 0.0010 - 402ms/epoch - 4ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.9994 - val_loss: 0.0645 - lr: 0.0010 - 424ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.9081 - val_loss: 0.0732 - lr: 0.0010 - 387ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.8459 - val_loss: 0.0826 - lr: 0.0010 - 429ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.8000 - val_loss: 0.0924 - lr: 0.0010 - 406ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7769 - val_loss: 0.0934 - lr: 1.0000e-04 - 404ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7734 - val_loss: 0.0945 - lr: 1.0000e-04 - 408ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7699 - val_loss: 0.0956 - lr: 1.0000e-04 - 390ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7663 - val_loss: 0.0967 - lr: 1.0000e-04 - 439ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7628 - val_loss: 0.0980 - lr: 1.0000e-04 - 399ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7606 - val_loss: 0.0981 - lr: 1.0000e-05 - 420ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7602 - val_loss: 0.0982 - lr: 1.0000e-05 - 413ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7599 - val_loss: 0.0983 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7595 - val_loss: 0.0985 - lr: 1.0000e-05 - 431ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7591 - val_loss: 0.0986 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7587 - val_loss: 0.0988 - lr: 1.0000e-05 - 418ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7583 - val_loss: 0.0989 - lr: 1.0000e-05 - 406ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7579 - val_loss: 0.0991 - lr: 1.0000e-05 - 395ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7575 - val_loss: 0.0992 - lr: 1.0000e-05 - 434ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7571 - val_loss: 0.0994 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7567 - val_loss: 0.0996 - lr: 1.0000e-05 - 422ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7563 - val_loss: 0.0997 - lr: 1.0000e-05 - 394ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7559 - val_loss: 0.0999 - lr: 1.0000e-05 - 394ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7555 - val_loss: 0.1001 - lr: 1.0000e-05 - 412ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7551 - val_loss: 0.1003 - lr: 1.0000e-05 - 398ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7546 - val_loss: 0.1005 - lr: 1.0000e-05 - 419ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7542 - val_loss: 0.1006 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7538 - val_loss: 0.1008 - lr: 1.0000e-05 - 396ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7534 - val_loss: 0.1010 - lr: 1.0000e-05 - 417ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7529 - val_loss: 0.1012 - lr: 1.0000e-05 - 384ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7525 - val_loss: 0.1014 - lr: 1.0000e-05 - 432ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7521 - val_loss: 0.1016 - lr: 1.0000e-05 - 406ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7517 - val_loss: 0.1018 - lr: 1.0000e-05 - 419ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7512 - val_loss: 0.1020 - lr: 1.0000e-05 - 405ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7508 - val_loss: 0.1022 - lr: 1.0000e-05 - 386ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7504 - val_loss: 0.1025 - lr: 1.0000e-05 - 417ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7500 - val_loss: 0.1027 - lr: 1.0000e-05 - 387ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7495 - val_loss: 0.1029 - lr: 1.0000e-05 - 405ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7491 - val_loss: 0.1031 - lr: 1.0000e-05 - 405ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7487 - val_loss: 0.1033 - lr: 1.0000e-05 - 382ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7482 - val_loss: 0.1035 - lr: 1.0000e-05 - 424ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7478 - val_loss: 0.1038 - lr: 1.0000e-05 - 381ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7474 - val_loss: 0.1040 - lr: 1.0000e-05 - 410ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7470 - val_loss: 0.1042 - lr: 1.0000e-05 - 410ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7465 - val_loss: 0.1045 - lr: 1.0000e-05 - 424ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7461 - val_loss: 0.1047 - lr: 1.0000e-05 - 434ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7457 - val_loss: 0.1049 - lr: 1.0000e-05 - 392ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7453 - val_loss: 0.1052 - lr: 1.0000e-05 - 422ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7448 - val_loss: 0.1054 - lr: 1.0000e-05 - 396ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05051
90/90 - 0s - loss: 0.7444 - val_loss: 0.1056 - lr: 1.0000e-05 - 402ms/epoch - 4ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.48% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 24.12057947793772 
RMSE:	 4.911270658183859 
MAPE:	 3.8711068958774497

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 36.227409389726965 
RMSE:	 6.018920948951479 
MAPE:	 4.70810831106621

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 47.6040579193988 
RMSE:	 6.8995694010132835 
MAPE:	 5.522605601178568

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 155.67335739769726 
RMSE:	 12.476912975479843 
MAPE:	 11.236116903479964

KAMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 19.84916238053282 
RMSE:	 4.45523987912355 
MAPE:	 3.572304554405335

MIDPOINT
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	46.27% Accuracy
MSE:	 21.813261360012138 
RMSE:	 4.67046693169025 
MAPE:	 3.6223152079979295

T3
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 67.60005597705626 
RMSE:	 8.221925320571591 
MAPE:	 6.604025072859764

TEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 24.243134917893084 
RMSE:	 4.923731808079425 
MAPE:	 4.330583242877685
Runtime: mins: 45.860193890400005

Architecture Used

In [ ]:
from google.colab import files
import cv2
uploaded = files.upload()
Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to enable. 
Saving Experiment8.png to Experiment8 (1).png
In [ ]:
img = cv2.imread('Experiment8.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

Model Plots

In [113]:
with open('simulation8_data.json') as json_file:
    simulation8 = json.load(json_file)
fileimg = 'Experiment8'
In [114]:
for i in range(len(list(simulation8.keys()))):
  SIM = list(simulation8.keys())[i]
  plot_train(simulation8,SIM)
  plot_test(simulation8,SIM)

----- Train RMSE for SMA ----- 20.144952693145125
----- Train_MSE_LSTM for SMA ----- 405.81911900905504
----- Train MAE LSTM for SMA ----- 20.137185568856722

----- Test RMSE for SMA----- 4.911270658183859
----- Test_MSE_LSTM for SMA----- 24.12057947793772
----- Test_MAE_LSTM for SMA----- 3.8711068958774497

----- Train RMSE for EMA ----- 24.237983942165165
----- Train_MSE_LSTM for EMA ----- 587.4798655806565
----- Train MAE LSTM for EMA ----- 24.233408446359164

----- Test RMSE for EMA----- 6.018920948951479
----- Test_MSE_LSTM for EMA----- 36.227409389726965
----- Test_MAE_LSTM for EMA----- 4.70810831106621

----- Train RMSE for WMA ----- 24.839096992968393
----- Train_MSE_LSTM for WMA ----- 616.9807394260914
----- Train MAE LSTM for WMA ----- 24.837005199772296

----- Test RMSE for WMA----- 6.8995694010132835
----- Test_MSE_LSTM for WMA----- 47.6040579193988
----- Test_MAE_LSTM for WMA----- 5.522605601178568

----- Train RMSE for DEMA ----- 26.637746302738936
----- Train_MSE_LSTM for DEMA ----- 709.5695280890818
----- Train MAE LSTM for DEMA ----- 26.62872602916

----- Test RMSE for DEMA----- 12.476912975479843
----- Test_MSE_LSTM for DEMA----- 155.67335739769726
----- Test_MAE_LSTM for DEMA----- 11.236116903479964

----- Train RMSE for KAMA ----- 20.429213713281705
----- Train_MSE_LSTM for KAMA ----- 417.35277294293724
----- Train MAE LSTM for KAMA ----- 20.425471756717947

----- Test RMSE for KAMA----- 4.45523987912355
----- Test_MSE_LSTM for KAMA----- 19.84916238053282
----- Test_MAE_LSTM for KAMA----- 3.572304554405335

----- Train RMSE for MIDPOINT ----- 16.856157067120407
----- Train_MSE_LSTM for MIDPOINT ----- 284.1300310714332
----- Train MAE LSTM for MIDPOINT ----- 16.801196841910333

----- Test RMSE for MIDPOINT----- 4.67046693169025
----- Test_MSE_LSTM for MIDPOINT----- 21.813261360012138
----- Test_MAE_LSTM for MIDPOINT----- 3.6223152079979295

----- Train RMSE for T3 ----- 23.819539505216678
----- Train_MSE_LSTM for T3 ----- 567.370462240578
----- Train MAE LSTM for T3 ----- 23.812523622323972

----- Test RMSE for T3----- 8.221925320571591
----- Test_MSE_LSTM for T3----- 67.60005597705626
----- Test_MAE_LSTM for T3----- 6.604025072859764

----- Train RMSE for TEMA ----- 20.0322994797993
----- Train_MSE_LSTM for TEMA ----- 401.2930224483673
----- Train MAE LSTM for TEMA ----- 19.998681748267447

----- Test RMSE for TEMA----- 4.923731808079425
----- Test_MSE_LSTM for TEMA----- 24.243134917893084
----- Test_MAE_LSTM for TEMA----- 4.330583242877685

List of RMSE, MSE & MAE scores for Test data

In [ ]:
import json
with open('simulation1_data.json') as json_file:
    simulation1 = json.load(json_file)

with open('simulation2_data.json') as json_file:
    simulation2 = json.load(json_file)

with open('simulation3_data.json') as json_file:
    simulation3 = json.load(json_file)

with open('simulation4_data.json') as json_file:
    simulation4 = json.load(json_file)

with open('simulation5_data.json') as json_file:
    simulation5 = json.load(json_file)

with open('simulation6_data.json') as json_file:
    simulation6 = json.load(json_file)

with open('simulation7_data.json') as json_file:
    simulation7 = json.load(json_file)

with open('simulation8_data.json') as json_file:
    simulation8 = json.load(json_file)
In [ ]:
text = 'Stock with Covid Trends '
simulations = [simulation1,simulation2,simulation3,simulation4,simulation5,simulation6,simulation7,simulation8]
for i,simulation in enumerate(simulations):
  for ma in simulation.keys():
    print(text+'Experiment ',i+1,' for MA :',ma,'the MSE  is: ',simulation[ma]['final']['mse'])
    print(text+'Experiment ',i+1,' for MA :',ma,'the RMSE is: ',simulation[ma]['final']['rmse'])
    print(text+'Experiment ',i+1,' for MA :',ma,'the MAE is: ',simulation[ma]['final']['mae'])

Stock with Covid Trends Experiment  1  for MA : SMA the MSE  is:  29.531169515594907
Stock with Covid Trends Experiment  1  for MA : SMA the RMSE is:  5.434258874547192
Stock with Covid Trends Experiment  1  for MA : SMA the MAE is:  4.511922179897357
Stock with Covid Trends Experiment  1  for MA : EMA the MSE  is:  44.2948843329178
Stock with Covid Trends Experiment  1  for MA : EMA the RMSE is:  6.655440205795392
Stock with Covid Trends Experiment  1  for MA : EMA the MAE is:  5.1903345685841265
Stock with Covid Trends Experiment  1  for MA : WMA the MSE  is:  34.81241095672678
Stock with Covid Trends Experiment  1  for MA : WMA the RMSE is:  5.900204314829002
Stock with Covid Trends Experiment  1  for MA : WMA the MAE is:  4.770935413189914
Stock with Covid Trends Experiment  1  for MA : DEMA the MSE  is:  52.107642174945944
Stock with Covid Trends Experiment  1  for MA : DEMA the RMSE is:  7.2185623343534235
Stock with Covid Trends Experiment  1  for MA : DEMA the MAE is:  5.72607728989529
Stock with Covid Trends Experiment  1  for MA : KAMA the MSE  is:  101.2314633840329
Stock with Covid Trends Experiment  1  for MA : KAMA the RMSE is:  10.06138476473457
Stock with Covid Trends Experiment  1  for MA : KAMA the MAE is:  7.671150891933135
Stock with Covid Trends Experiment  1  for MA : MIDPOINT the MSE  is:  120.91184599154492
Stock with Covid Trends Experiment  1  for MA : MIDPOINT the RMSE is:  10.995992269529154
Stock with Covid Trends Experiment  1  for MA : MIDPOINT the MAE is:  9.137686493675425
Stock with Covid Trends Experiment  1  for MA : T3 the MSE  is:  41.51394815576297
Stock with Covid Trends Experiment  1  for MA : T3 the RMSE is:  6.443131859256255
Stock with Covid Trends Experiment  1  for MA : T3 the MAE is:  5.507945991108928
Stock with Covid Trends Experiment  1  for MA : TEMA the MSE  is:  72.3302204365722
Stock with Covid Trends Experiment  1  for MA : TEMA the RMSE is:  8.504717540081634
Stock with Covid Trends Experiment  1  for MA : TEMA the MAE is:  7.413730210152267
Stock with Covid Trends Experiment  2  for MA : SMA the MSE  is:  63.041023819643854
Stock with Covid Trends Experiment  2  for MA : SMA the RMSE is:  7.939837770360541
Stock with Covid Trends Experiment  2  for MA : SMA the MAE is:  6.449589599500938
Stock with Covid Trends Experiment  2  for MA : EMA the MSE  is:  63.66877348603133
Stock with Covid Trends Experiment  2  for MA : EMA the RMSE is:  7.979271488427457
Stock with Covid Trends Experiment  2  for MA : EMA the MAE is:  6.567170782771208
Stock with Covid Trends Experiment  2  for MA : WMA the MSE  is:  74.84193590201411
Stock with Covid Trends Experiment  2  for MA : WMA the RMSE is:  8.65112338959595
Stock with Covid Trends Experiment  2  for MA : WMA the MAE is:  6.92726320779593
Stock with Covid Trends Experiment  2  for MA : DEMA the MSE  is:  124.07774757087437
Stock with Covid Trends Experiment  2  for MA : DEMA the RMSE is:  11.139019147612341
Stock with Covid Trends Experiment  2  for MA : DEMA the MAE is:  9.962964959911572
Stock with Covid Trends Experiment  2  for MA : KAMA the MSE  is:  64.92528911521055
Stock with Covid Trends Experiment  2  for MA : KAMA the RMSE is:  8.057623043752454
Stock with Covid Trends Experiment  2  for MA : KAMA the MAE is:  6.682416615913553
Stock with Covid Trends Experiment  2  for MA : MIDPOINT the MSE  is:  68.19255604013144
Stock with Covid Trends Experiment  2  for MA : MIDPOINT the RMSE is:  8.25787842246006
Stock with Covid Trends Experiment  2  for MA : MIDPOINT the MAE is:  6.72839330666561
Stock with Covid Trends Experiment  2  for MA : T3 the MSE  is:  149.0300312328299
Stock with Covid Trends Experiment  2  for MA : T3 the RMSE is:  12.207785680983669
Stock with Covid Trends Experiment  2  for MA : T3 the MAE is:  10.094975187792123
Stock with Covid Trends Experiment  2  for MA : TEMA the MSE  is:  71.80641753112648
Stock with Covid Trends Experiment  2  for MA : TEMA the RMSE is:  8.473866740227066
Stock with Covid Trends Experiment  2  for MA : TEMA the MAE is:  7.512371017185029
Stock with Covid Trends Experiment  3  for MA : SMA the MSE  is:  123.96893050522607
Stock with Covid Trends Experiment  3  for MA : SMA the RMSE is:  11.134133576764116
Stock with Covid Trends Experiment  3  for MA : SMA the MAE is:  9.602398807260117
Stock with Covid Trends Experiment  3  for MA : EMA the MSE  is:  63.919262026708296
Stock with Covid Trends Experiment  3  for MA : EMA the RMSE is:  7.994952284204596
Stock with Covid Trends Experiment  3  for MA : EMA the MAE is:  6.479287961204322
Stock with Covid Trends Experiment  3  for MA : WMA the MSE  is:  24.651058301828286
Stock with Covid Trends Experiment  3  for MA : WMA the RMSE is:  4.9649832126431495
Stock with Covid Trends Experiment  3  for MA : WMA the MAE is:  3.9308905500983484
Stock with Covid Trends Experiment  3  for MA : DEMA the MSE  is:  156.8635759091866
Stock with Covid Trends Experiment  3  for MA : DEMA the RMSE is:  12.524518989134338
Stock with Covid Trends Experiment  3  for MA : DEMA the MAE is:  11.387412907589542
Stock with Covid Trends Experiment  3  for MA : KAMA the MSE  is:  59.19746610115158
Stock with Covid Trends Experiment  3  for MA : KAMA the RMSE is:  7.69398895899595
Stock with Covid Trends Experiment  3  for MA : KAMA the MAE is:  6.776737847872761
Stock with Covid Trends Experiment  3  for MA : MIDPOINT the MSE  is:  46.490023595118274
Stock with Covid Trends Experiment  3  for MA : MIDPOINT the RMSE is:  6.818359303756166
Stock with Covid Trends Experiment  3  for MA : MIDPOINT the MAE is:  5.538801606657957
Stock with Covid Trends Experiment  3  for MA : T3 the MSE  is:  57.75776139981352
Stock with Covid Trends Experiment  3  for MA : T3 the RMSE is:  7.59985272224492
Stock with Covid Trends Experiment  3  for MA : T3 the MAE is:  6.172107202063374
Stock with Covid Trends Experiment  3  for MA : TEMA the MSE  is:  61.81638170069383
Stock with Covid Trends Experiment  3  for MA : TEMA the RMSE is:  7.862339454684835
Stock with Covid Trends Experiment  3  for MA : TEMA the MAE is:  7.157520441443416
Stock with Covid Trends Experiment  4  for MA : SMA the MSE  is:  22.0961825771905
Stock with Covid Trends Experiment  4  for MA : SMA the RMSE is:  4.700657674963207
Stock with Covid Trends Experiment  4  for MA : SMA the MAE is:  3.7488296078488137
Stock with Covid Trends Experiment  4  for MA : EMA the MSE  is:  36.69312385194829
Stock with Covid Trends Experiment  4  for MA : EMA the RMSE is:  6.057484944426053
Stock with Covid Trends Experiment  4  for MA : EMA the MAE is:  4.755707959713801
Stock with Covid Trends Experiment  4  for MA : WMA the MSE  is:  61.47074835668693
Stock with Covid Trends Experiment  4  for MA : WMA the RMSE is:  7.8403283321992925
Stock with Covid Trends Experiment  4  for MA : WMA the MAE is:  6.468176158698829
Stock with Covid Trends Experiment  4  for MA : DEMA the MSE  is:  114.21230424130383
Stock with Covid Trends Experiment  4  for MA : DEMA the RMSE is:  10.687015684525958
Stock with Covid Trends Experiment  4  for MA : DEMA the MAE is:  9.305044543155903
Stock with Covid Trends Experiment  4  for MA : KAMA the MSE  is:  21.57120658320832
Stock with Covid Trends Experiment  4  for MA : KAMA the RMSE is:  4.6444813040002995
Stock with Covid Trends Experiment  4  for MA : KAMA the MAE is:  3.6837316829247877
Stock with Covid Trends Experiment  4  for MA : MIDPOINT the MSE  is:  17.38125304406819
Stock with Covid Trends Experiment  4  for MA : MIDPOINT the RMSE is:  4.169082997982673
Stock with Covid Trends Experiment  4  for MA : MIDPOINT the MAE is:  3.3993243705608664
Stock with Covid Trends Experiment  4  for MA : T3 the MSE  is:  60.321913944220896
Stock with Covid Trends Experiment  4  for MA : T3 the RMSE is:  7.766718351029661
Stock with Covid Trends Experiment  4  for MA : T3 the MAE is:  6.200911576902634
Stock with Covid Trends Experiment  4  for MA : TEMA the MSE  is:  25.760985062606874
Stock with Covid Trends Experiment  4  for MA : TEMA the RMSE is:  5.075528057513511
Stock with Covid Trends Experiment  4  for MA : TEMA the MAE is:  4.549137795705406
Stock with Covid Trends Experiment  5  for MA : SMA the MSE  is:  36.387272258848725
Stock with Covid Trends Experiment  5  for MA : SMA the RMSE is:  6.032186358100081
Stock with Covid Trends Experiment  5  for MA : SMA the MAE is:  4.990569235256131
Stock with Covid Trends Experiment  5  for MA : EMA the MSE  is:  72.47565418845511
Stock with Covid Trends Experiment  5  for MA : EMA the RMSE is:  8.513263427643661
Stock with Covid Trends Experiment  5  for MA : EMA the MAE is:  6.94585827976211
Stock with Covid Trends Experiment  5  for MA : WMA the MSE  is:  29.73090246364654
Stock with Covid Trends Experiment  5  for MA : WMA the RMSE is:  5.452605107987057
Stock with Covid Trends Experiment  5  for MA : WMA the MAE is:  4.390044818690696
Stock with Covid Trends Experiment  5  for MA : DEMA the MSE  is:  39.142904723518775
Stock with Covid Trends Experiment  5  for MA : DEMA the RMSE is:  6.256429071244936
Stock with Covid Trends Experiment  5  for MA : DEMA the MAE is:  4.920393911559133
Stock with Covid Trends Experiment  5  for MA : KAMA the MSE  is:  52.56428057408519
Stock with Covid Trends Experiment  5  for MA : KAMA the RMSE is:  7.25012279717283
Stock with Covid Trends Experiment  5  for MA : KAMA the MAE is:  6.170488218753182
Stock with Covid Trends Experiment  5  for MA : MIDPOINT the MSE  is:  44.21016710593271
Stock with Covid Trends Experiment  5  for MA : MIDPOINT the RMSE is:  6.649072650071791
Stock with Covid Trends Experiment  5  for MA : MIDPOINT the MAE is:  5.476790088019583
Stock with Covid Trends Experiment  5  for MA : T3 the MSE  is:  64.94642382025489
Stock with Covid Trends Experiment  5  for MA : T3 the RMSE is:  8.058934409725326
Stock with Covid Trends Experiment  5  for MA : T3 the MAE is:  6.415762745110697
Stock with Covid Trends Experiment  5  for MA : TEMA the MSE  is:  29.21500753639505
Stock with Covid Trends Experiment  5  for MA : TEMA the RMSE is:  5.4050908906691895
Stock with Covid Trends Experiment  5  for MA : TEMA the MAE is:  4.44965723634719
Stock with Covid Trends Experiment  6  for MA : SMA the MSE  is:  60.485697397526344
Stock with Covid Trends Experiment  6  for MA : SMA the RMSE is:  7.777255132598284
Stock with Covid Trends Experiment  6  for MA : SMA the MAE is:  6.358945125308518
Stock with Covid Trends Experiment  6  for MA : EMA the MSE  is:  58.20305175219876
Stock with Covid Trends Experiment  6  for MA : EMA the RMSE is:  7.629092459277103
Stock with Covid Trends Experiment  6  for MA : EMA the MAE is:  6.21442849961768
Stock with Covid Trends Experiment  6  for MA : WMA the MSE  is:  70.88350276857014
Stock with Covid Trends Experiment  6  for MA : WMA the RMSE is:  8.419234096316014
Stock with Covid Trends Experiment  6  for MA : WMA the MAE is:  6.6789569931753
Stock with Covid Trends Experiment  6  for MA : DEMA the MSE  is:  119.53246002468391
Stock with Covid Trends Experiment  6  for MA : DEMA the RMSE is:  10.933090140700566
Stock with Covid Trends Experiment  6  for MA : DEMA the MAE is:  9.747683697911842
Stock with Covid Trends Experiment  6  for MA : KAMA the MSE  is:  61.13308833987969
Stock with Covid Trends Experiment  6  for MA : KAMA the RMSE is:  7.818765141624327
Stock with Covid Trends Experiment  6  for MA : KAMA the MAE is:  6.461585168646619
Stock with Covid Trends Experiment  6  for MA : MIDPOINT the MSE  is:  61.5384692642518
Stock with Covid Trends Experiment  6  for MA : MIDPOINT the RMSE is:  7.8446458979517875
Stock with Covid Trends Experiment  6  for MA : MIDPOINT the MAE is:  6.407298993379305
Stock with Covid Trends Experiment  6  for MA : T3 the MSE  is:  163.02597008234568
Stock with Covid Trends Experiment  6  for MA : T3 the RMSE is:  12.768162361214932
Stock with Covid Trends Experiment  6  for MA : T3 the MAE is:  10.498544939048504
Stock with Covid Trends Experiment  6  for MA : TEMA the MSE  is:  66.14227466119469
Stock with Covid Trends Experiment  6  for MA : TEMA the RMSE is:  8.132790090811067
Stock with Covid Trends Experiment  6  for MA : TEMA the MAE is:  7.1170786919128775
Stock with Covid Trends Experiment  7  for MA : SMA the MSE  is:  23.38002191723926
Stock with Covid Trends Experiment  7  for MA : SMA the RMSE is:  4.835289227878645
Stock with Covid Trends Experiment  7  for MA : SMA the MAE is:  3.8675720673818827
Stock with Covid Trends Experiment  7  for MA : EMA the MSE  is:  35.056668726825066
Stock with Covid Trends Experiment  7  for MA : EMA the RMSE is:  5.920867227596399
Stock with Covid Trends Experiment  7  for MA : EMA the MAE is:  4.704877912816018
Stock with Covid Trends Experiment  7  for MA : WMA the MSE  is:  44.87192646385527
Stock with Covid Trends Experiment  7  for MA : WMA the RMSE is:  6.698651092858566
Stock with Covid Trends Experiment  7  for MA : WMA the MAE is:  5.33068935026581
Stock with Covid Trends Experiment  7  for MA : DEMA the MSE  is:  53.079656203261706
Stock with Covid Trends Experiment  7  for MA : DEMA the RMSE is:  7.285578645739933
Stock with Covid Trends Experiment  7  for MA : DEMA the MAE is:  5.726487515550782
Stock with Covid Trends Experiment  7  for MA : KAMA the MSE  is:  30.678794294842323
Stock with Covid Trends Experiment  7  for MA : KAMA the RMSE is:  5.5388441298561855
Stock with Covid Trends Experiment  7  for MA : KAMA the MAE is:  4.336649130448084
Stock with Covid Trends Experiment  7  for MA : MIDPOINT the MSE  is:  19.38951232132957
Stock with Covid Trends Experiment  7  for MA : MIDPOINT the RMSE is:  4.4033523957695655
Stock with Covid Trends Experiment  7  for MA : MIDPOINT the MAE is:  3.5042510250586574
Stock with Covid Trends Experiment  7  for MA : T3 the MSE  is:  90.72292612095576
Stock with Covid Trends Experiment  7  for MA : T3 the RMSE is:  9.524858325505727
Stock with Covid Trends Experiment  7  for MA : T3 the MAE is:  7.398189805001564
Stock with Covid Trends Experiment  7  for MA : TEMA the MSE  is:  46.925505559638836
Stock with Covid Trends Experiment  7  for MA : TEMA the RMSE is:  6.850219380402268
Stock with Covid Trends Experiment  7  for MA : TEMA the MAE is:  5.67920042842036
Stock with Covid Trends Experiment  8  for MA : SMA the MSE  is:  24.12057947793772
Stock with Covid Trends Experiment  8  for MA : SMA the RMSE is:  4.911270658183859
Stock with Covid Trends Experiment  8  for MA : SMA the MAE is:  3.8711068958774497
Stock with Covid Trends Experiment  8  for MA : EMA the MSE  is:  36.227409389726965
Stock with Covid Trends Experiment  8  for MA : EMA the RMSE is:  6.018920948951479
Stock with Covid Trends Experiment  8  for MA : EMA the MAE is:  4.70810831106621
Stock with Covid Trends Experiment  8  for MA : WMA the MSE  is:  47.6040579193988
Stock with Covid Trends Experiment  8  for MA : WMA the RMSE is:  6.8995694010132835
Stock with Covid Trends Experiment  8  for MA : WMA the MAE is:  5.522605601178568
Stock with Covid Trends Experiment  8  for MA : DEMA the MSE  is:  155.67335739769726
Stock with Covid Trends Experiment  8  for MA : DEMA the RMSE is:  12.476912975479843
Stock with Covid Trends Experiment  8  for MA : DEMA the MAE is:  11.236116903479964
Stock with Covid Trends Experiment  8  for MA : KAMA the MSE  is:  19.84916238053282
Stock with Covid Trends Experiment  8  for MA : KAMA the RMSE is:  4.45523987912355
Stock with Covid Trends Experiment  8  for MA : KAMA the MAE is:  3.572304554405335
Stock with Covid Trends Experiment  8  for MA : MIDPOINT the MSE  is:  21.813261360012138
Stock with Covid Trends Experiment  8  for MA : MIDPOINT the RMSE is:  4.67046693169025
Stock with Covid Trends Experiment  8  for MA : MIDPOINT the MAE is:  3.6223152079979295
Stock with Covid Trends Experiment  8  for MA : T3 the MSE  is:  67.60005597705626
Stock with Covid Trends Experiment  8  for MA : T3 the RMSE is:  8.221925320571591
Stock with Covid Trends Experiment  8  for MA : T3 the MAE is:  6.604025072859764
Stock with Covid Trends Experiment  8  for MA : TEMA the MSE  is:  24.243134917893084
Stock with Covid Trends Experiment  8  for MA : TEMA the RMSE is:  4.923731808079425
Stock with Covid Trends Experiment  8  for MA : TEMA the MAE is:  4.330583242877685
In [ ]:
text = 'Stock with Covid Trends '
simulations = [simulation1,simulation2,simulation3,simulation4,simulation5,simulation6,simulation7,simulation8]
for i,simulation in enumerate(simulations):
  for ma in simulation.keys():
    # print(text+'Experiment ',i+1,' for MA :',ma,'the MSE  is: ',simulation[ma]['final']['mse'])
    print(text+'Experiment ',i+1,' for MA :',ma,'the RMSE is: ',simulation[ma]['final']['rmse'])
    # print(text+'Experiment ',i+1,' for MA :',ma,'the MAE is: ',simulation[ma]['final']['mae'])
  for ma in simulation.keys():
    print(text+'Experiment ',i+1,' for MA :',ma,'the MSE  is: ',simulation[ma]['final']['mse'])
    # print(text+'Experiment ',i+1,' for MA :',ma,'the RMSE is: ',simulation[ma]['final']['rmse'])
    # print(text+'Experiment ',i+1,' for MA :',ma,'the MAE is: ',simulation[ma]['final']['mae'])
  for ma in simulation.keys():
    # print(text+'Experiment ',i+1,' for MA :',ma,'the MSE  is: ',simulation[ma]['final']['mse'])
    # print(text+'Experiment ',i+1,' for MA :',ma,'the RMSE is: ',simulation[ma]['final']['rmse'])
    print(text+'Experiment ',i+1,' for MA :',ma,'the MAE is: ',simulation[ma]['final']['mae'])

Stock with Covid Trends Experiment  1  for MA : SMA the RMSE is:  5.434258874547192
Stock with Covid Trends Experiment  1  for MA : EMA the RMSE is:  6.655440205795392
Stock with Covid Trends Experiment  1  for MA : WMA the RMSE is:  5.900204314829002
Stock with Covid Trends Experiment  1  for MA : DEMA the RMSE is:  7.2185623343534235
Stock with Covid Trends Experiment  1  for MA : KAMA the RMSE is:  10.06138476473457
Stock with Covid Trends Experiment  1  for MA : MIDPOINT the RMSE is:  10.995992269529154
Stock with Covid Trends Experiment  1  for MA : T3 the RMSE is:  6.443131859256255
Stock with Covid Trends Experiment  1  for MA : TEMA the RMSE is:  8.504717540081634
Stock with Covid Trends Experiment  1  for MA : SMA the MSE  is:  29.531169515594907
Stock with Covid Trends Experiment  1  for MA : EMA the MSE  is:  44.2948843329178
Stock with Covid Trends Experiment  1  for MA : WMA the MSE  is:  34.81241095672678
Stock with Covid Trends Experiment  1  for MA : DEMA the MSE  is:  52.107642174945944
Stock with Covid Trends Experiment  1  for MA : KAMA the MSE  is:  101.2314633840329
Stock with Covid Trends Experiment  1  for MA : MIDPOINT the MSE  is:  120.91184599154492
Stock with Covid Trends Experiment  1  for MA : T3 the MSE  is:  41.51394815576297
Stock with Covid Trends Experiment  1  for MA : TEMA the MSE  is:  72.3302204365722
Stock with Covid Trends Experiment  1  for MA : SMA the MAE is:  4.511922179897357
Stock with Covid Trends Experiment  1  for MA : EMA the MAE is:  5.1903345685841265
Stock with Covid Trends Experiment  1  for MA : WMA the MAE is:  4.770935413189914
Stock with Covid Trends Experiment  1  for MA : DEMA the MAE is:  5.72607728989529
Stock with Covid Trends Experiment  1  for MA : KAMA the MAE is:  7.671150891933135
Stock with Covid Trends Experiment  1  for MA : MIDPOINT the MAE is:  9.137686493675425
Stock with Covid Trends Experiment  1  for MA : T3 the MAE is:  5.507945991108928
Stock with Covid Trends Experiment  1  for MA : TEMA the MAE is:  7.413730210152267
Stock with Covid Trends Experiment  2  for MA : SMA the RMSE is:  7.939837770360541
Stock with Covid Trends Experiment  2  for MA : EMA the RMSE is:  7.979271488427457
Stock with Covid Trends Experiment  2  for MA : WMA the RMSE is:  8.65112338959595
Stock with Covid Trends Experiment  2  for MA : DEMA the RMSE is:  11.139019147612341
Stock with Covid Trends Experiment  2  for MA : KAMA the RMSE is:  8.057623043752454
Stock with Covid Trends Experiment  2  for MA : MIDPOINT the RMSE is:  8.25787842246006
Stock with Covid Trends Experiment  2  for MA : T3 the RMSE is:  12.207785680983669
Stock with Covid Trends Experiment  2  for MA : TEMA the RMSE is:  8.473866740227066
Stock with Covid Trends Experiment  2  for MA : SMA the MSE  is:  63.041023819643854
Stock with Covid Trends Experiment  2  for MA : EMA the MSE  is:  63.66877348603133
Stock with Covid Trends Experiment  2  for MA : WMA the MSE  is:  74.84193590201411
Stock with Covid Trends Experiment  2  for MA : DEMA the MSE  is:  124.07774757087437
Stock with Covid Trends Experiment  2  for MA : KAMA the MSE  is:  64.92528911521055
Stock with Covid Trends Experiment  2  for MA : MIDPOINT the MSE  is:  68.19255604013144
Stock with Covid Trends Experiment  2  for MA : T3 the MSE  is:  149.0300312328299
Stock with Covid Trends Experiment  2  for MA : TEMA the MSE  is:  71.80641753112648
Stock with Covid Trends Experiment  2  for MA : SMA the MAE is:  6.449589599500938
Stock with Covid Trends Experiment  2  for MA : EMA the MAE is:  6.567170782771208
Stock with Covid Trends Experiment  2  for MA : WMA the MAE is:  6.92726320779593
Stock with Covid Trends Experiment  2  for MA : DEMA the MAE is:  9.962964959911572
Stock with Covid Trends Experiment  2  for MA : KAMA the MAE is:  6.682416615913553
Stock with Covid Trends Experiment  2  for MA : MIDPOINT the MAE is:  6.72839330666561
Stock with Covid Trends Experiment  2  for MA : T3 the MAE is:  10.094975187792123
Stock with Covid Trends Experiment  2  for MA : TEMA the MAE is:  7.512371017185029
Stock with Covid Trends Experiment  3  for MA : SMA the RMSE is:  11.134133576764116
Stock with Covid Trends Experiment  3  for MA : EMA the RMSE is:  7.994952284204596
Stock with Covid Trends Experiment  3  for MA : WMA the RMSE is:  4.9649832126431495
Stock with Covid Trends Experiment  3  for MA : DEMA the RMSE is:  12.524518989134338
Stock with Covid Trends Experiment  3  for MA : KAMA the RMSE is:  7.69398895899595
Stock with Covid Trends Experiment  3  for MA : MIDPOINT the RMSE is:  6.818359303756166
Stock with Covid Trends Experiment  3  for MA : T3 the RMSE is:  7.59985272224492
Stock with Covid Trends Experiment  3  for MA : TEMA the RMSE is:  7.862339454684835
Stock with Covid Trends Experiment  3  for MA : SMA the MSE  is:  123.96893050522607
Stock with Covid Trends Experiment  3  for MA : EMA the MSE  is:  63.919262026708296
Stock with Covid Trends Experiment  3  for MA : WMA the MSE  is:  24.651058301828286
Stock with Covid Trends Experiment  3  for MA : DEMA the MSE  is:  156.8635759091866
Stock with Covid Trends Experiment  3  for MA : KAMA the MSE  is:  59.19746610115158
Stock with Covid Trends Experiment  3  for MA : MIDPOINT the MSE  is:  46.490023595118274
Stock with Covid Trends Experiment  3  for MA : T3 the MSE  is:  57.75776139981352
Stock with Covid Trends Experiment  3  for MA : TEMA the MSE  is:  61.81638170069383
Stock with Covid Trends Experiment  3  for MA : SMA the MAE is:  9.602398807260117
Stock with Covid Trends Experiment  3  for MA : EMA the MAE is:  6.479287961204322
Stock with Covid Trends Experiment  3  for MA : WMA the MAE is:  3.9308905500983484
Stock with Covid Trends Experiment  3  for MA : DEMA the MAE is:  11.387412907589542
Stock with Covid Trends Experiment  3  for MA : KAMA the MAE is:  6.776737847872761
Stock with Covid Trends Experiment  3  for MA : MIDPOINT the MAE is:  5.538801606657957
Stock with Covid Trends Experiment  3  for MA : T3 the MAE is:  6.172107202063374
Stock with Covid Trends Experiment  3  for MA : TEMA the MAE is:  7.157520441443416
Stock with Covid Trends Experiment  4  for MA : SMA the RMSE is:  4.700657674963207
Stock with Covid Trends Experiment  4  for MA : EMA the RMSE is:  6.057484944426053
Stock with Covid Trends Experiment  4  for MA : WMA the RMSE is:  7.8403283321992925
Stock with Covid Trends Experiment  4  for MA : DEMA the RMSE is:  10.687015684525958
Stock with Covid Trends Experiment  4  for MA : KAMA the RMSE is:  4.6444813040002995
Stock with Covid Trends Experiment  4  for MA : MIDPOINT the RMSE is:  4.169082997982673
Stock with Covid Trends Experiment  4  for MA : T3 the RMSE is:  7.766718351029661
Stock with Covid Trends Experiment  4  for MA : TEMA the RMSE is:  5.075528057513511
Stock with Covid Trends Experiment  4  for MA : SMA the MSE  is:  22.0961825771905
Stock with Covid Trends Experiment  4  for MA : EMA the MSE  is:  36.69312385194829
Stock with Covid Trends Experiment  4  for MA : WMA the MSE  is:  61.47074835668693
Stock with Covid Trends Experiment  4  for MA : DEMA the MSE  is:  114.21230424130383
Stock with Covid Trends Experiment  4  for MA : KAMA the MSE  is:  21.57120658320832
Stock with Covid Trends Experiment  4  for MA : MIDPOINT the MSE  is:  17.38125304406819
Stock with Covid Trends Experiment  4  for MA : T3 the MSE  is:  60.321913944220896
Stock with Covid Trends Experiment  4  for MA : TEMA the MSE  is:  25.760985062606874
Stock with Covid Trends Experiment  4  for MA : SMA the MAE is:  3.7488296078488137
Stock with Covid Trends Experiment  4  for MA : EMA the MAE is:  4.755707959713801
Stock with Covid Trends Experiment  4  for MA : WMA the MAE is:  6.468176158698829
Stock with Covid Trends Experiment  4  for MA : DEMA the MAE is:  9.305044543155903
Stock with Covid Trends Experiment  4  for MA : KAMA the MAE is:  3.6837316829247877
Stock with Covid Trends Experiment  4  for MA : MIDPOINT the MAE is:  3.3993243705608664
Stock with Covid Trends Experiment  4  for MA : T3 the MAE is:  6.200911576902634
Stock with Covid Trends Experiment  4  for MA : TEMA the MAE is:  4.549137795705406
Stock with Covid Trends Experiment  5  for MA : SMA the RMSE is:  6.032186358100081
Stock with Covid Trends Experiment  5  for MA : EMA the RMSE is:  8.513263427643661
Stock with Covid Trends Experiment  5  for MA : WMA the RMSE is:  5.452605107987057
Stock with Covid Trends Experiment  5  for MA : DEMA the RMSE is:  6.256429071244936
Stock with Covid Trends Experiment  5  for MA : KAMA the RMSE is:  7.25012279717283
Stock with Covid Trends Experiment  5  for MA : MIDPOINT the RMSE is:  6.649072650071791
Stock with Covid Trends Experiment  5  for MA : T3 the RMSE is:  8.058934409725326
Stock with Covid Trends Experiment  5  for MA : TEMA the RMSE is:  5.4050908906691895
Stock with Covid Trends Experiment  5  for MA : SMA the MSE  is:  36.387272258848725
Stock with Covid Trends Experiment  5  for MA : EMA the MSE  is:  72.47565418845511
Stock with Covid Trends Experiment  5  for MA : WMA the MSE  is:  29.73090246364654
Stock with Covid Trends Experiment  5  for MA : DEMA the MSE  is:  39.142904723518775
Stock with Covid Trends Experiment  5  for MA : KAMA the MSE  is:  52.56428057408519
Stock with Covid Trends Experiment  5  for MA : MIDPOINT the MSE  is:  44.21016710593271
Stock with Covid Trends Experiment  5  for MA : T3 the MSE  is:  64.94642382025489
Stock with Covid Trends Experiment  5  for MA : TEMA the MSE  is:  29.21500753639505
Stock with Covid Trends Experiment  5  for MA : SMA the MAE is:  4.990569235256131
Stock with Covid Trends Experiment  5  for MA : EMA the MAE is:  6.94585827976211
Stock with Covid Trends Experiment  5  for MA : WMA the MAE is:  4.390044818690696
Stock with Covid Trends Experiment  5  for MA : DEMA the MAE is:  4.920393911559133
Stock with Covid Trends Experiment  5  for MA : KAMA the MAE is:  6.170488218753182
Stock with Covid Trends Experiment  5  for MA : MIDPOINT the MAE is:  5.476790088019583
Stock with Covid Trends Experiment  5  for MA : T3 the MAE is:  6.415762745110697
Stock with Covid Trends Experiment  5  for MA : TEMA the MAE is:  4.44965723634719
Stock with Covid Trends Experiment  6  for MA : SMA the RMSE is:  7.777255132598284
Stock with Covid Trends Experiment  6  for MA : EMA the RMSE is:  7.629092459277103
Stock with Covid Trends Experiment  6  for MA : WMA the RMSE is:  8.419234096316014
Stock with Covid Trends Experiment  6  for MA : DEMA the RMSE is:  10.933090140700566
Stock with Covid Trends Experiment  6  for MA : KAMA the RMSE is:  7.818765141624327
Stock with Covid Trends Experiment  6  for MA : MIDPOINT the RMSE is:  7.8446458979517875
Stock with Covid Trends Experiment  6  for MA : T3 the RMSE is:  12.768162361214932
Stock with Covid Trends Experiment  6  for MA : TEMA the RMSE is:  8.132790090811067
Stock with Covid Trends Experiment  6  for MA : SMA the MSE  is:  60.485697397526344
Stock with Covid Trends Experiment  6  for MA : EMA the MSE  is:  58.20305175219876
Stock with Covid Trends Experiment  6  for MA : WMA the MSE  is:  70.88350276857014
Stock with Covid Trends Experiment  6  for MA : DEMA the MSE  is:  119.53246002468391
Stock with Covid Trends Experiment  6  for MA : KAMA the MSE  is:  61.13308833987969
Stock with Covid Trends Experiment  6  for MA : MIDPOINT the MSE  is:  61.5384692642518
Stock with Covid Trends Experiment  6  for MA : T3 the MSE  is:  163.02597008234568
Stock with Covid Trends Experiment  6  for MA : TEMA the MSE  is:  66.14227466119469
Stock with Covid Trends Experiment  6  for MA : SMA the MAE is:  6.358945125308518
Stock with Covid Trends Experiment  6  for MA : EMA the MAE is:  6.21442849961768
Stock with Covid Trends Experiment  6  for MA : WMA the MAE is:  6.6789569931753
Stock with Covid Trends Experiment  6  for MA : DEMA the MAE is:  9.747683697911842
Stock with Covid Trends Experiment  6  for MA : KAMA the MAE is:  6.461585168646619
Stock with Covid Trends Experiment  6  for MA : MIDPOINT the MAE is:  6.407298993379305
Stock with Covid Trends Experiment  6  for MA : T3 the MAE is:  10.498544939048504
Stock with Covid Trends Experiment  6  for MA : TEMA the MAE is:  7.1170786919128775
Stock with Covid Trends Experiment  7  for MA : SMA the RMSE is:  4.835289227878645
Stock with Covid Trends Experiment  7  for MA : EMA the RMSE is:  5.920867227596399
Stock with Covid Trends Experiment  7  for MA : WMA the RMSE is:  6.698651092858566
Stock with Covid Trends Experiment  7  for MA : DEMA the RMSE is:  7.285578645739933
Stock with Covid Trends Experiment  7  for MA : KAMA the RMSE is:  5.5388441298561855
Stock with Covid Trends Experiment  7  for MA : MIDPOINT the RMSE is:  4.4033523957695655
Stock with Covid Trends Experiment  7  for MA : T3 the RMSE is:  9.524858325505727
Stock with Covid Trends Experiment  7  for MA : TEMA the RMSE is:  6.850219380402268
Stock with Covid Trends Experiment  7  for MA : SMA the MSE  is:  23.38002191723926
Stock with Covid Trends Experiment  7  for MA : EMA the MSE  is:  35.056668726825066
Stock with Covid Trends Experiment  7  for MA : WMA the MSE  is:  44.87192646385527
Stock with Covid Trends Experiment  7  for MA : DEMA the MSE  is:  53.079656203261706
Stock with Covid Trends Experiment  7  for MA : KAMA the MSE  is:  30.678794294842323
Stock with Covid Trends Experiment  7  for MA : MIDPOINT the MSE  is:  19.38951232132957
Stock with Covid Trends Experiment  7  for MA : T3 the MSE  is:  90.72292612095576
Stock with Covid Trends Experiment  7  for MA : TEMA the MSE  is:  46.925505559638836
Stock with Covid Trends Experiment  7  for MA : SMA the MAE is:  3.8675720673818827
Stock with Covid Trends Experiment  7  for MA : EMA the MAE is:  4.704877912816018
Stock with Covid Trends Experiment  7  for MA : WMA the MAE is:  5.33068935026581
Stock with Covid Trends Experiment  7  for MA : DEMA the MAE is:  5.726487515550782
Stock with Covid Trends Experiment  7  for MA : KAMA the MAE is:  4.336649130448084
Stock with Covid Trends Experiment  7  for MA : MIDPOINT the MAE is:  3.5042510250586574
Stock with Covid Trends Experiment  7  for MA : T3 the MAE is:  7.398189805001564
Stock with Covid Trends Experiment  7  for MA : TEMA the MAE is:  5.67920042842036
Stock with Covid Trends Experiment  8  for MA : SMA the RMSE is:  4.911270658183859
Stock with Covid Trends Experiment  8  for MA : EMA the RMSE is:  6.018920948951479
Stock with Covid Trends Experiment  8  for MA : WMA the RMSE is:  6.8995694010132835
Stock with Covid Trends Experiment  8  for MA : DEMA the RMSE is:  12.476912975479843
Stock with Covid Trends Experiment  8  for MA : KAMA the RMSE is:  4.45523987912355
Stock with Covid Trends Experiment  8  for MA : MIDPOINT the RMSE is:  4.67046693169025
Stock with Covid Trends Experiment  8  for MA : T3 the RMSE is:  8.221925320571591
Stock with Covid Trends Experiment  8  for MA : TEMA the RMSE is:  4.923731808079425
Stock with Covid Trends Experiment  8  for MA : SMA the MSE  is:  24.12057947793772
Stock with Covid Trends Experiment  8  for MA : EMA the MSE  is:  36.227409389726965
Stock with Covid Trends Experiment  8  for MA : WMA the MSE  is:  47.6040579193988
Stock with Covid Trends Experiment  8  for MA : DEMA the MSE  is:  155.67335739769726
Stock with Covid Trends Experiment  8  for MA : KAMA the MSE  is:  19.84916238053282
Stock with Covid Trends Experiment  8  for MA : MIDPOINT the MSE  is:  21.813261360012138
Stock with Covid Trends Experiment  8  for MA : T3 the MSE  is:  67.60005597705626
Stock with Covid Trends Experiment  8  for MA : TEMA the MSE  is:  24.243134917893084
Stock with Covid Trends Experiment  8  for MA : SMA the MAE is:  3.8711068958774497
Stock with Covid Trends Experiment  8  for MA : EMA the MAE is:  4.70810831106621
Stock with Covid Trends Experiment  8  for MA : WMA the MAE is:  5.522605601178568
Stock with Covid Trends Experiment  8  for MA : DEMA the MAE is:  11.236116903479964
Stock with Covid Trends Experiment  8  for MA : KAMA the MAE is:  3.572304554405335
Stock with Covid Trends Experiment  8  for MA : MIDPOINT the MAE is:  3.6223152079979295
Stock with Covid Trends Experiment  8  for MA : T3 the MAE is:  6.604025072859764
Stock with Covid Trends Experiment  8  for MA : TEMA the MAE is:  4.330583242877685

Create HTML

In [ ]:
cd ..
In [ ]:
cd drive/MyDrive/Stock price prediction/Archana - LSTM Hybrid
In [ ]:
%%shell
jupyter nbconvert --to html LSTM_Hybrid_using_TA_LIB_Covid.ipynb